historynews.md

💥 History News

2024

☄️ EgoAlpha releases the TrustGPT focuses on reasoning. Trust the GPT with the strongest reasoning abilities for authentic and reliable answers. You can click here or visit the Playgrounds directly to experience it。

[2024.9.12]

• Paper: Alt-MoE: Multimodal Alignment via Alternating Optimization of Multi-directional MoE with Unimodal Models

[2024.9.11]

• Paper: Assessing SPARQL capabilities of Large Language Models

[2024.9.10]

• Paper: OPAL: Outlier-Preserved Microscaling Quantization A ccelerator for Generative Large Language Models

[2024.9.9]

• Paper: Propaganda to Hate: A Multimodal Analysis of Arabic Memes with Multi-Agent LLMs

[2024.9.8]

• Paper: Large Language Models and the Extended Church-Turing Thesis

[2024.9.7]

• Paper: General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

[2024.9.6]

• Tech giants fight voice model battle! Amazon upgrades Alexa with Claude, Cerebras voice model is lightning fast

[2024.9.5]

• Paper: HiPrompt: Tuning-free Higher-Resolution Generation with Hierarchical MLLM Prompts

[2024.9.4]

• Paper: Configurable Foundation Models: Building LLMs from a Modular Perspective

[2024.9.3]

• Survey Paper: Towards a Unified View of Preference Learning for Large Language Models: A Survey

[2024.9.2]

• Paper: Predicting the Impact of Generative AI Using an Agent-Based Model

[2024.9.1]

• Paper: Bridging Domain Knowledge and Process Discovery Using Large Language Models

[2024.8.31]

• Paper: Open-vocabulary Temporal Action Localization using VLMs

[2024.8.30]

• Paper: DARES: Depth Anything in Robotic Endoscopic Surgery with Self-supervised Vector-LoRA of the Foundation Model

[2024.8.29]

• Paper: LLMs as Zero-shot Graph Learners: Alignment of GNN Representations with LLM Token Embeddings

[2024.8.28]

• Survey Paper: Unveiling the Statistical Foundations of Chain-of-Thought Prompting Methods

[2024.8.27]

• Paper: A New Era in Computational Pathology: A Survey on Foundation and Vision-Language Models

[2024.8.26]

• Paper: CHARTOM: A Visual Theory-of-Mind Benchmark for Multimodal Large Language Models

[2024.8.25]

• Paper: Language-specific Calibration for Pruning Multilingual Language Models

[2024.8.24]

• Paper: Enhancing Depression Diagnosis with Chain-of-Thought Prompting

[2024.8.23]

• Paper: MLR-Copilot: Autonomous Machine Learning Research based on Large Language Models Agents

[2024.8.22]

• Paper: LMM-VQA: Advancing Video Quality Assessment with Large Multimodal Models

[2024.8.21]

• Paper: AgentMove: Predicting Human Mobility Anywhere Using Large Language Model based Agentic Framework

[2024.8.20]

• Paper: Geo-Llama: Leveraging LLMs for Human Mobility Trajectory Generation with Spatiotemporal Constraints

[2024.8.19]

• Paper: LLaVA-Surg: Towards Multimodal Surgical Assistant via Structured Surgical Video Learning

[2024.8.18]

• Paper: FuseChat: Knowledge Fusion of Chat Models

[2024.8.17]

• Paper: mhGPT: A Lightweight Generative Pre-Trained Transformer for Mental Health Text Analysis

[2024.8.16]

• Paper: Autonomous Behavior Planning For Humanoid Loco-manipulation Through Grounded Language Model

[2024.8.15]

• Technical Report: Can Large Language Models Understand Symbolic Graphics Programs?

[2024.8.14]

• Paper: LLM4DSR: Leveraing Large Language Model for Denoising Sequential Recommendation

[2024.8.13]

• Paper: When Video Coding Meets Multimodal Large Language Models: A Unified Paradigm for Video Coding

[2024.8.12]

• Survey Paper: Preserving Privacy in Large Language Models: A Survey on Current Threats and Solutions

[2024.8.11]

• Paper: VITA: Towards Open-Source Interactive Omni Multimodal LLM

[2024.8.10]

• Paper: TaSL: Task Skill Localization and Consolidation for Language Model Continual Learning

[2024.8.9]

• Paper: How Well Do LLMs Identify Cultural Unity in Diversity?

[2024.8.8]

• Paper: Hyperbolic Learning with Multimodal Large Language Models

[2024.8.7]

• Paper: Instruction Tuning-free Visual Token Complement for Multimodal LLMs

[2024.8.6]

• Paper: ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation

[2024.8.5]

• Paper: Prompt Recursive Search: A Living Framework with Adaptive Growth in LLM Auto-Prompting
• Paper: Toward Automatic Relevance Judgment using Vision--Language Models for Image--Text Retrieval Evaluation

[2024.8.4]

• Paper: Talk Less, Interact Better: Evaluating In-context Conversational Adaptation in Multimodal LLMs

[2024.8.3]

• Paper: Coalitions of Large Language Models Increase the Robustness of AI Agents

[2024.8.2]

• Paper: Large-scale AI performance art: 'Humans stop' posting, 17 large models spamming like crazy

[2024.8.1]

• Paper: LLM4CP: Adapting Large Language Models for Channel Prediction

[2024.7.31]

• Paper: UrbanGPT: Spatio-Temporal Large Language Models

[2024.7.30]

• 🔥🔥🔥Apple's AI version of iOS is hot on its first day

[2024.7.29] -🔥🔥🔥Paper: Wolf: Captioning Everything with a World Summarization Framework

[2024.7.28]

• Paper: The Dark Side of Function Calling: Pathways to Jailbreaking Large Language Models

[2024.7.27]

• 🔥🔥🔥The GPT-4o mini is a power hog and costs nothing to fine-tune for a limited time of 2 months!

[2024.7.26]

• Paper: ChatSchema: A pipeline of extracting structured information with Large Multimodal Models based on schema

[2024.7.25]

• Paper: The power of Prompts: Evaluating and Mitigating Gender Bias in MT with LLMs

[2024.7.24]

• 🔥🔥🔥Open source beats closed source, llama3.1 reaches T0 level

[2024.7.23]

• 🔥🔥🔥OpenAI kicks off miniatures bloodbath! Apple's DCLM comes on strong, crushes Mistral 7B full open source

[2024.7.22]

• Paper: LLMmap: Fingerprinting For Large Language Models

[2024.7.21]

• Paper: SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models

[2024.7.20]

• Paper: Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition

[2024.7.19]

• 🔥🔥🔥OpenAI introduces new lightweight quantisation model GPT-4o mini

[2024.7.18]

• Mistral AI has just launched its first open source model based on the Mamba2 architecture, Codestral Mamba (7B), specialising in code generation.
• Paper: Black-Box Opinion Manipulation Attacks to Retrieval-Augmented Generation of Large Language Models

[2024.7.17]

• Paper: The Two Sides of the Coin: Hallucination Generation and Detection with LLMs as Evaluators for LLMs

[2024.7.16]

• 🔥🔥🔥Open Source! The world's largest AI-based model for pathology is here!

[2024.7.15]

• 🔥🔥🔥The world's first big open-source model for chip design is born! 5 years to reshape the $500 billion semiconductor industry!
• Paper: On LLM Wizards: Identifying Large Language Models' Behaviors for Wizard of Oz Experiments

[2024.7.14]

• 🔥🔥🔥The Big Model Authority Test was exposed as a flop! Favouring closed source models such as GPT-4 even more, even the cue words are treated differently
• Paper: RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization

[2024.7.13]

• Paper: FairyLandAI: Personalized Fairy Tales utilizing ChatGPT and DALLE-3

[2024.7.12]

• Paper: MUSCLE: A Model Update Strategy for Compatible LLM Evolution

[2024.7.11]

• 🔥🔥🔥NVIDIA release: PaperData, Data Everywhere:A Guide for Pretraining Dataset Construction

[2024.7.10]

• Paper: Multi-Object Hallucination in Vision-Language Models

[2024.7.9]

• Paper: Video-STaR: Self-Training Enables Video Instruction Tuning with Any Supervision

[2024.7.8]

• Paper: Temporal Grounding of Activities using Multimodal Large Language Models

[2024.7.7]

• 🔥🔥🔥WAIC：2024:Only spend 2 minutes, the requirements document into a product, China's large model development artefacts fire WAIC

[2024.7.6]

• 🔥🔥🔥 Gemma 2 is the strongest open-source model, surpassing Llama 3!
• Paper: IncogniText: Privacy-enhancing Conditional Text Anonymization via LLM-based Private Attribute Randomization

[2024.7.5]

• Paper: InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output

[2024.7.4]

• Paper: Cooperative Multi-Agent Deep Reinforcement Learning Methods for UAV-aided Mobile Edge Computing Networks

[2024.7.3]

• Paper: TheoremLlama: Transforming General-Purpose LLMs into Lean4 Experts

[2024.7.2]

• Technical Paper: Motion meets Attention: Video Motion Prompts

[2024.7.1]

• Paper: Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs

[2024.6.30]

• Paper: LLaRA: Supercharging Robot Learning Data for Vision-Language Policy
• Paper: Token Erasure as a Footprint of Implicit Vocabulary Items in LLMs

[2024.6.29]

• Paper: LLaVolta: Efficient Multi-modal Models via Stage-wise Visual Context Compression

[2024.6.28]

• Paper: Dataset Size Recovery from LoRA Weights

[2024.6.27]

• Paper: OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding

[2024.6.26]

• Paper: Fundamental Problems With Model Editing: How Should Rational Belief Revision Work in LLMs?
• Paper: PrExMe! Large Scale Prompt Exploration of Open Source LLMs for Machine Translation and Summarization Evaluation

[2024.6.25]

• Paper: Symbolic Learning Enables Self-Evolving Agents

[2024.6.24]

• Paper: The Remarkable Robustness of LLMs: Stages of Inference?

[2024.6.23]

• Paper: Efficient World Models with Context-Aware Tokenization

[2024.6.22]

• Paper: Revisiting Referring Expression Comprehension Evaluation in the Era of Large Multimodal Models

[2024.6.21]

• Paper: Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs

[2024.6.20]

• Paper: LaMDA: Large Model Fine-Tuning via Spectrally Decomposed Low-Dimensional Adaptation
• Paper: From RAGs to rich parameters: Probing how language models utilize external knowledge over parametric information for factual queries

[2024.6.19]

• Paper: Adversarial Attacks on Multimodal Agents
• Paper: AITTI: Learning Adaptive Inclusive Token for Text-to-Image Generation

[2024.6.18]

• Paper: LLaNA: Large Language and NeRF Assistant

[2024.6.17]

• Paper: Unveiling Encoder-Free Vision-Language Models
• Paper: VideoLLM-online: Online Video Large Language Model for Streaming Video

[2024.6.16]

• Paper: RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Content

[2024.6.15]

• Paper: VEGA: Learning Interleaved Image-Text Comprehension in Vision-Language Large Models
• Paper: EFM3D: A Benchmark for Measuring Progress Towards 3D Egocentric Foundation Models

[2024.6.14]

• Paper: Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs

[2024.6.13]

• Paper: Beyond LLaVA-HD: Diving into High-Resolution Large Multimodal Models
• Paper: Enhancing End-to-End Autonomous Driving with Latent World Model

[2024.6.12]

• Paper: Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing
• Paper: The Impact of Initialization on LoRA Finetuning Dynamics

[2024.6.11]

• Paper: Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation
• Paper: Can Language Models Serve as Text-Based World Simulators?【ACL2024】

[2024.6.10]

• Survey Paper: Towards a Personal Health Large Language Model
• Technical Report: Husky: A Unified, Open-Source Language Agent for Multi-Step Reasoning

[2024.6.9]

• Paper: 3D-GRAND: Towards Better Grounding and Less Hallucination for 3D-LLMs
  • Technical Report: Towards Semantic Equivalence of Tokenization in Multimodal LLM

[2024.6.8]

• Paper: An Empirical Study on Parameter-Efficient Fine-Tuning for MultiModal Large Language Models

[2024.6.7]

• Paper: Language models emulate certain cognitive profiles: An investigation of how predictability measures interact with individual differences【ACL2024】

[2024.6.6]

• Paper: Verbalized Machine Learning: Revisiting Machine Learning with Language Models
• Paper: PaCE: Parsimonious Concept Engineering for Large Language Models

[2024.6.5]

• Paper: Seq1F1B: Efficient Sequence-Level Pipeline Parallelism for Large Language Model Training

[2024.6.4]

• Paper: Learning to grok: Emergence of in-context learning and skill composition in modular arithmetic tasks
• Paper: Leveraging Visual Tokens for Extended Text Contexts in Multi-Modal Learning

[2024.6.3]

• Paper: Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis
• Paper: Graph External Attention Enhanced Transformer【ICML2024】

[2024.6.2]

• Paper: Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality【ICML2024】
• Paper: LACIE: Listener-Aware Finetuning for Confidence Calibration in Large Language Models

[2024.6.1]

• Paper: StrucTexTv3: An Efficient Vision-Language Model for Text-rich Image Perception, Comprehension, and Beyond
• Paper: DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

[2024.5.31]

• Paper: Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Training
• Paper: OR-Bench: An Over-Refusal Benchmark for Large Language Models

[2024.5.30]

• Paper: Visualizing the loss landscape of Self-supervised Vision Transformer【NIPS2024 workshop】
• Paper: TimeChara: Evaluating Point-in-Time Character Hallucination of Role-Playing Large Language Models【ACL2024】

[2024.5.29]

• Paper: Cross-Context Backdoor Attacks against Graph Prompt Learning【KDD2024】
• Paper: Yuan 2.0-M32: Mixture of Experts with Attention Router

[2024.5.28]

• Survey Paper: Tool Learning with Large Language Models: A Survey
• Paper: Long Context is Not Long at All: A Prospector of Long-Dependency Data for Large Language Models

[2024.5.27]

• Paper: Subtle Biases Need Subtler Measures: Dual Metrics for Evaluating Representative and Affinity Bias in Large Language Models【ACL2024】
• Paper: Exploring Alignment in Shared Cross-lingual Spaces【ACL2024】

[2024.5.26]

• Paper: ConvLLaVA: Hierarchical Backbones as Visual Encoder for Large Multimodal Models
• Paper: Disease-informed Adaptation of Vision-Language Models【MICCAI 2024】

[2024.5.25]

• Paper: Chain-of-Thought Prompting for Demographic Inference with Large Multimodal Models【ICME2024】
• Paper: Prompt-Aware Adapter: Towards Learning Adaptive Visual Tokens for Multimodal Large Language Models

[2024.5.24]

• Paper: Neuromorphic dreaming: A pathway to efficient learning in artificial agents
• Paper: DAGER: Exact Gradient Inversion for Large Language Models

[2024.5.23]

• Paper: Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models
• Paper: When Generative AI Meets Workplace Learning: Creating A Realistic & Motivating Learning Experience With A Generative PCA【ECIS2024】

[2024.5.22]

• Paper: MAML-en-LLM: Model Agnostic Meta-Training of LLMs for Improved In-Context Learning【KDD2024】
• Paper: Measuring Impacts of Poisoning on Model Parameters and Embeddings for Large Language Models of Code【1st ACM International Conference on AI-powered Software (AIware), co-located with the ACM International Conference on the Foundations of Software Engineering (FSE) 2024, Porto de Galinhas, Brazil. 】
• Paper: Effective In-Context Example Selection through Data Compression【ACL2024】

[2024.5.21]

• Paper: Efficient Prompt Tuning by Multi-Space Projection and Prompt Fusion
• Paper: CPS-LLM: Large Language Model based Safe Usage Plan Generator for Human-in-the-Loop Human-in-the-Plant Cyber-Physical System【AAAI2024】
• Paper:DocReLM: Mastering Document Retrieval with Language Model

[2024.5.20]

• Paper: Libra: Building Decoupled Vision System on Large Language Models
• Paper: Unsupervised Image Prior via Prompt Learning and CLIP Semantic Guidance for Low-Light Image Enhancement【CVPR 2024 Workshop NTIRE: New Trends in Image Restoration and Enhancement workshop and Challenges】
• Paper: MarkLLM: An Open-Source Toolkit for LLM Watermarking

[2024.5.19]

• Paper: Revisiting OPRO: The Limitations of Small-Scale LLMs as Optimizers
• Survey Paper: When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models

[2024.5.18]

• Paper: HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language Models
• Paper: Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning

[2024.5.17]

• Paper: UniRAG: Universal Retrieval Augmentation for Multi-Modal Large Language Models
• Paper: Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection

[2024.5.16]

• Paper: Text-to-Vector Generation with Neural Path Representation
• Paper: Analogist: Out-of-the-box Visual In-Context Learning with Image Diffusion Model

[2024.5.15]

• 🔥🔥🔥Google strikes back: Project Astra goes head-to-head with GPT-4o, Veo fights Sora, and a new version of Gemini revolutionises search
• Paper: Improving Transformers with Dynamically Composable Multi-Head Attention
• Paper: Learning Multi-Agent Communication from Graph Modeling Perspective

[2024.5.14]

• 🔥🔥🔥OpenAI Turns the World Upside Down: GPT-4o is Completely Free, Real-Time Voice-Video Interaction Rocks the Room
• Paper: Efficient Vision-Language Pre-training by Cluster Masking
• Paper: Promoting AI Equity in Science: Generalized Domain Prompt Learning for Accessible VLM Research

[2024.5.13]

• Paper: Linearizing Large Language Models
• Paper: Multimodal LLMs Struggle with Basic Visual Network Analysis: a VNA Benchmark

[2024.5.12]

• Paper: UniDM: A Unified Framework for Data Manipulation with Large Language Models
• Paper: Storypark: Leveraging Large Language Models to Enhance Children Story Learning Through Child-AI collaboration Storytelling

[2024.5.11]

• Paper: Pseudo-Prompt Generating in Pre-trained Vision-Language Models for Multi-Label Medical Image Classification

[2024.5.10]

• Paper: FlockGPT: Guiding UAV Flocking with Linguistic Orchestration
• Paper: An Automatic Prompt Generation System for Tabular Data Tasks
• Paper: Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning

[2024.5.9]

• Paper: Probing Multimodal LLMs as World Models for Driving
• Paper: Smurfs: Leveraging Multiple Proficiency Agents with Context-Efficiency for Tool Planning
• Paper: Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformers

[2024.5.8]

• Paper: ChatHuman: Language-driven 3D Human Understanding with Retrieval-Augmented Tool Reasoning
• Paper: QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving
• Paper: Unveiling Disparities in Web Task Handling Between Human and Web Agent

[2024.5.7]

• Paper: vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention
• Paper: DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
• Survey Paper: Vision Mamba: A Comprehensive Survey and Taxonomy

[2024.5.6]

• Paper: Vibe-Eval: A hard evaluation suite for measuring progress of multimodal language models
• Paper: On the test-time zero-shot generalization of vision-language models: Do we really need prompt learning?
• Paper: Leveraging Large Language Models to Enhance Domain Expert Inclusion in Data Science Workflows

[2024.5.5]

• Paper: What matters when building vision-language models?
• Paper: REASONS: A benchmark for REtrieval and Automated citationS Of scieNtific Sentences using Public and Proprietary LLMs
• Paper: FairEvalLLM. A Comprehensive Framework for Benchmarking Fairness in Large Language Model Recommender Systems

[2024.5.4]

• Paper: Single and Multi-Hop Question-Answering Datasets for Reticular Chemistry with GPT-4-Turbo
• Paper: Analyzing Narrative Processing in Large Language Models (LLMs): Using GPT4 to test BERT
• Paper: Auto-Encoding Morph-Tokens for Multimodal LLM

[2024.5.3]

• Paper: Self-Refine Instruction-Tuning for Aligning Reasoning in Language Models
• Paper: CofiPara: A Coarse-to-fine Paradigm for Multimodal Sarcasm Target Identification with Large Multimodal Models
• Paper: AdaMoLE: Fine-Tuning Large Language Models with Adaptive Mixture of Low-Rank Adaptation Experts

[2024.5.2]

• Paper: When Quantization Affects Confidence of Large Language Models?
• Paper: Causal Evaluation of Language Models
• Paper: Investigating Automatic Scoring and Feedback using Large Language Models

[2024.5.1]

• Paper: Self-Play Preference Optimization for Language Model Alignment
• Paper: Is Bigger Edit Batch Size Always Better? -- An Empirical Study on Model Editing with Llama-3
• Paper: RST-LoRA: A Discourse-Aware Low-Rank Adaptation for Long Document Abstractive Summarization

[2024.4.30]

• Paper: EALD-MLLM: Emotion Analysis in Long-sequential and De-identity videos with Multi-modal Large Language Model
• Paper: NumLLM: Numeric-Sensitive Large Language Model for Chinese Finance
• Paper: Navigating WebAI: Training Agents to Complete Web Tasks with Large Language Models and Reinforcement Learning

[2024.4.29]

• The "Chinese NVIDIA" thousand-card cluster is now in place.
• XVERSE-V: Unconditionally commercial free, outperforms Claude 3 Sonnet

[2024.4.28]

• Paper: Learning to Beat ByteRL: Exploitability of Collectible Card Game Agents
• Paper: Unifying Asynchronous Logics for Hyperproperties
• Paper: Lost in Recursion: Mining Rich Event Semantics in Knowledge Graphs

[2024.4.27]

• Paper: AAPL: Adding Attributes to Prompt Learning for Vision-Language Models
• Paper: SEED-Bench-2-Plus: Benchmarking Multimodal Large Language Models with Text-Rich Visual Comprehension
• Paper: Cooperate or Collapse: Emergence of Sustainability Behaviors in a Society of LLM Agents

[2024.4.26]

• Paper: IndicGenBench: A Multilingual Benchmark to Evaluate Generation Capabilities of LLMs on Indic Languages
• Paper: Make Your LLM Fully Utilize the Context
• Paper: Improving Diversity of Commonsense Generation by Large Language Models via In-Context Learning

[2024.4.25]

• Paper: Cantor: Inspiring Multimodal Chain-of-Thought of MLLM
• Paper: The PRISM Alignment Project: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models
• Paper: MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI

[2024.4.24]

• Survey Paper: A Survey on Visual Mamba
• Paper: Uncertainty Estimation and Quantification for LLMs: A Simple Supervised Approach
• Paper: Exploring LLM Prompting Strategies for Joint Essay Scoring and Feedback Generation

[2024.4.23]

• Paper: Re-Thinking Inverse Graphics With Large Language Models
  • Paper: Does Instruction Tuning Make LLMs More Consistent?

[2024.4.22]

• Paper: Unified Scene Representation and Reconstruction for 3D Large Language Models
• Paper: Sample Design Engineering: An Empirical Study of What Makes Good Downstream Fine-Tuning Samples for LLMs
• Paper: Stronger Random Baselines for In-Context Learning

[2024.4.21]

• Paper: When LLMs are Unfit Use FastFit: Fast and Effective Text Classification with Many Classes
• Paper: Rethinking the Evaluation of Dialogue Systems: Effects of User Feedback on Crowdworkers and LLMs
• Paper: Private Agent-Based Modeling

[2024.4.20]

• 🔥🔥🔥Introducing Meta Llama 3: The most capable openly available LLM to date
• Paper: Towards Reliable Latent Knowledge Estimation in LLMs: In-Context Learning vs. Prompting Based Factual Knowledge Extraction

[2024.4.19]

• Paper: V2Xum-LLM: Cross-Modal Video Summarization with Temporal Prompt Instruction Tuning
• Paper: Point-In-Context: Understanding Point Cloud via In-Context Learning
• Paper: Omniview-Tuning: Boosting Viewpoint Invariance of Vision-Language Pre-training Models

[2024.4.18]

• Paper: Quantifying Multilingual Performance of Large Language Models Across Languages
• Paper: Moving Object Segmentation: All You Need Is SAM (and Flow)
• Paper: When LLMs are Unfit Use FastFit: Fast and Effective Text Classification with Many Classes

[2024.4.17]

• Paper: Prompt Optimizer of Text-to-Image Diffusion Models for Abstract Concept Understanding
• Survey Paper: The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey
• Paper: LLMTune: Accelerate Database Knob Tuning with Large Language Models

[2024.4.16]

• Paper: MMInA: Benchmarking Multihop Multimodal Internet Agents
• Paper: Memory Sharing for Large Language Model based Agents
• Paper: LLMorpheus: Mutation Testing using Large Language Models

[2024.4.15]

• Paper: Superposition Prompting: Improving and Accelerating Retrieval-Augmented Generation
• Paper: BRAVE: Broadening the visual encoding of vision-language models
• Paper: From Model-centered to Human-Centered: Revision Distance as a Metric for Text Evaluation in LLMs-based Applications

[2024.4.14]

• Paper: ExeGPT: Constraint-Aware Resource Scheduling for LLM Inference
• Paper: ORacle: Large Vision-Language Models for Knowledge-Guided Holistic OR Domain Modeling
• Paper: MetaCheckGPT -- A Multi-task Hallucination Detector Using LLM Uncertainty and Meta-models

[2024.4.13]

• Paper: OpenBias: Open-set Bias Detection in Text-to-Image Generative Models
• Paper: Any2Point: Empowering Any-modality Large Models for Efficient 3D Understanding
• Paper: Manipulating Large Language Models to Increase Product Visibility

[2024.4.12]

• Paper: RecurrentGemma: Moving Past Transformers for Efficient Open Language Models
• Paper: Generating consistent PDDL domains with Large Language Models
• Paper: ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models

[2024.4.11]

• Paper: ExeGPT: Constraint-Aware Resource Scheduling for LLM Inference
• Paper: InfiCoder-Eval: Systematically Evaluating the Question-Answering Capabilities of Code Large Language Models
• Paper: High-Dimension Human Value Representation in Large Language Models

[2024.4.10]

• Paper: OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
• Paper: EduAgent: Generative Student Agents in Learning
• Paper: Content Knowledge Identification with Multi-Agent Large Language Models (LLMs)

[2024.4.9]

• Paper: Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs
• Paper: MoMA: Multimodal LLM Adapter for Fast Personalized Image Generation
• Paper: MIMIR: A Streamlined Platform for Personalized Agent Tuning in Domain Expertise

[2024.4.8]

• Paper: Long-horizon Locomotion and Manipulation on a Quadrupedal Robot with Large Language Models
• Paper: LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding
• Paper: DLoRA: Distributed Parameter-Efficient Fine-Tuning Solution for Large Language Model

[2024.4.7]

• Paper: LongVLM: Efficient Long Video Understanding via Large Language Models
• Paper: nicolay-r at SemEval-2024 Task 3: Using Flan-T5 for Reasoning Emotion Cause in Conversations with Chain-of-Thought on Emotion States
• Paper: Do Large Language Models Rank Fairly? An Empirical Study on the Fairness of LLMs as Rankers

[2024.4.6]

• Paper: Can Small Language Models Help Large Language Models Reason Better?: LM-Guided Chain-of-Thought
• Paper: MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens
• Paper: Scaling Up Video Summarization Pretraining with Large Language Models

[2024.4.5]

• Paper:Evaluating LLMs at Detecting Errors in LLM Responses
• Paper:Laser Learning Environment: A new environment for coordination-critical multi-agent tasks
• Paper:Untangle the KNOT: Interweaving Conflicting Knowledge and Reasoning Skills in Large Language Models

[2024.4.4]

• Paper:AutoWebGLM: Bootstrap And Reinforce A Large Language Model-based Web Navigating Agent
• Paper:Unveiling LLMs: The Evolution of Latent Representations in a Temporal Knowledge Graph
• Paper:Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models

[2024.4.3]

• Paper: Topic-based Watermarks for LLM-Generated Text
• Paper: ViTamin: Designing Scalable Vision Models in the Vision-Language Era
• Paper: Pre-trained Vision and Language Transformers Are Few-Shot Incremental Learners

[2024.4.2]

• Paper: Segment Any 3D Object with Language
• Paper: Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks
• Paper: Iterated Learning Improves Compositionality in Large Vision-Language Models

[2024.4.1]

• Paper: LUQ: Long-text Uncertainty Quantification for LLMs
• Paper: ELITR-Bench: A Meeting Assistant Benchmark for Long-Context Language Models
• Paper: ChatGPT v.s. Media Bias: A Comparative Study of GPT-3.5 and Fine-tuned Language Models

[2024.3.31]

• Paper: MTLoRA: A Low-Rank Adaptation Approach for Efficient Multi-Task Learning
• Paper: Convolutional Prompting meets Language Models for Continual Learning
• Paper: Towards Greener LLMs: Bringing Energy-Efficiency to the Forefront of LLM Inference

[2024.3.30]

• Paper: Unsolvable Problem Detection: Evaluating Trustworthiness of Vision Language Models
• Paper: ReALM: Reference Resolution As Language Modeling
• Paper: Gecko: Versatile Text Embeddings Distilled from Large Language Models

[2024.3.29]

• Paper: RSMamba: Remote Sensing Image Classification with State Space Model
• Paper: Change-Agent: Towards Interactive Comprehensive Change Interpretation and Analysis from Change Detection and Change Captioning
• Paper: WaterJudge: Quality-Detection Trade-off when Watermarking Large Language Models

[2024.3.28]

• Paper: Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models
• Paper: 3P-LLM: Probabilistic Path Planning using Large Language Model for Autonomous Robot Navigation
• Paper: MLDT: Multi-Level Decomposition for Complex Long-Horizon Robotic Task Planning with Open-Source Large Language Model

[2024.3.27]

• 🔥🔥🔥Stability AI open-sources 3B code generation model: it's patchable, and it can Debug
• 🔥🔥🔥Suno, the "AI Songwriter", is a hit in the music industry.
• Paper: TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document

[2024.3.26]

• Paper: AIOS: LLM Agent Operating System
• Paper: Bayesian Methods for Trust in Collaborative Multi-Agent Autonomy
• Paper: Multi-Agent Optimization for Safety Analysis of Cyber-Physical Systems: Position Paper

[2024.3.25]

• Paper: DreamLIP: Language-Image Pre-training with Long Captions
• Paper: Visual CoT: Unleashing Chain-of-Thought Reasoning in Multi-Modal Language Models
• Paper: Comp4D: LLM-Guided Compositional 4D Scene Generation

[2024.3.24]

• 🔥🔥🔥Paper: SC-Tune: Unleashing Self-Consistent Referential Comprehension in Large Vision Language Models
• Paper: Enhancing Code Generation Performance of Smaller Models by Distilling the Reasoning Ability of LLMs
• Paper: AFLoRA: Adaptive Freezing of Low Rank Adaptation in Parameter Efficient Fine-Tuning of Large Models

[2024.3.23]

• Paper: SAMCT: Segment Any CT Allowing Labor-Free Task-Indicator Prompts
• Paper: Instruction Multi-Constraint Molecular Generation Using a Teacher-Student Large Language Model
• Paper: Towards Robots That Know When They Need Help: Affordance-Based Uncertainty for Large Language Model Planners

[2024.3.22]

• Paper: MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?
• Paper: Hierarchical Text-to-Vision Self Supervised Alignment for Improved Histopathology Representation Learning
• Survey Paper: Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey

[2024.3.21]

• Paper: MyVLM: Personalizing VLMs for User-Specific Queries
• Paper: PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model
• Paper: ReAct Meets ActRe: Autonomous Annotations of Agent Trajectories for Contrastive Self-Training

[2024.3.20]

• Paper: A Chain-of-Thought Prompting Approach with LLMs for Evaluating Students' Formative Assessment Responses in Science
• Survey Paper: The Ethics of ChatGPT in Medicine and Healthcare: A Systematic Review on Large Language Models (LLMs)
• Survey Paper: ChatGPT Alternative Solutions: Large Language Models Survey

[2024.3.19]

• 🔥🔥🔥Nvidia GTC
• 🔥🔥🔥Open Release of Grok-1
• Paper: VideoAgent: Long-form Video Understanding with Large Language Model as Agent
• Paper: Few-Shot Class Incremental Learning with Attention-Aware Self-Adaptive Prompt

[2024.3.18]

• Paper: The First to Know: How Token Distributions Reveal Hidden Knowledge in Large Vision-Language Models?
• Paper: ChartInstruct: Instruction Tuning for Chart Comprehension and Reasoning
• Paper: LoRA-SP: Streamlined Partial Parameter Adaptation for Resource-Efficient Fine-Tuning of Large Language Models

[2024.3.17]

• Paper: Unveiling the Generalization Power of Fine-Tuned Large Language Models
• Paper: Towards Proactive Interactions for In-Vehicle Conversational Assistants Utilizing Large Language Models
• Paper: UniCode: Learning a Unified Codebook for Multimodal Large Language Models

[2024.3.16]

• Paper: Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference
• Paper: Simple and Scalable Strategies to Continually Pre-train Large Language Models
• Paper: SOTOPIA-π: Interactive Learning of Socially Intelligent Language Agents

[2024.3.15]

• Paper: ExploRLLM: Guiding Exploration in Reinforcement Learning with Large Language Models
• Paper: Big City Bias: Evaluating the Impact of Metropolitan Size on Computational Job Market Abilities of Language Models
• Paper: LG-Traj: LLM Guided Pedestrian Trajectory Prediction

[2024.3.14]

• 🔥🔥🔥Speak, See and Act, OpenAI Robotics
• Paper: 3D-VLA: A 3D Vision-Language-Action Generative World Model
• Paper: MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training
• Survey Paper: Large Language Models and Causal Inference in Collaboration: A Comprehensive Survey

[2024.3.13]

• 🔥🔥🔥The world first AGI agents! Introducing Devin, the first AI software engineer
• 🔥🔥🔥Paper: Towards General Computer Control: A Multimodal Agent for Red Dead Redemption II as a Case Study
• Paper: DeepSafeMPC: Deep Learning-Based Model Predictive Control for Safe Multi-Agent Reinforcement Learning
• 🔥🔥🔥Paper: VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models
• Paper: NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning

[2024.3.12]

• Paper: Attention Prompt Tuning: Parameter-efficient Adaptation of Pre-trained Models for Spatiotemporal Modeling
• Paper: VideoMamba: State Space Model for Efficient Video Understanding
• Paper: Naming, Describing, and Quantifying Visual Objects in Humans and LLMs
• Paper: ERA-CoT: Improving Chain-of-Thought through Entity Relationship Analysis

[2024.3.11]

• 🔥🔥🔥Inflection-2.5 Release: The Ultimate Big Model
• Paper:LLM4Decompile: Decompiling Binary Code with Large Language Models
• Paper:ERBench: An Entity-Relationship based Automatically Verifiable Hallucination Benchmark for Large Language Models

[2024.3.10]

• Paper:Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought
• Paper:Cost-Performance Optimization for Processing Low-Resource Language Tasks Using Commercial LLMs
• Paper:VLM-PL: Advanced Pseudo Labeling approach Class Incremental Object Detection with Vision-Language Model

[2024.3.9]

• Paper:Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference
• Paper:Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
• Paper:DeepSeek-VL: Towards Real-World Vision-Language Understanding

[2024.3.8]

• Survey Paper: Benchmarking the Text-to-SQL Capability of Large Language Models: A Comprehensive Evaluation
• Survey Paper: A Comprehensive Survey on Process-Oriented Automatic Text Summarization with Exploration of LLM-Based Methods
• Paper: Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models
• Paper: Localized Zeroth-Order Prompt Optimization

[2024.3.7]

• Paper: Mamba4Rec: Towards Efficient Sequential Recommendation with Selective State Space Models
• Paper: SaulLM-7B: A pioneering Large Language Model for Law
• Paper: On the Origins of Linear Representations in Large Language Models
• Paper: Model Parallelism on Distributed Infrastructure: A Literature Review from Theory to LLM Case-Studies
• Paper: Automatic Bi-modal Question Title Generation for Stack Overflow with Prompt Learning

[2024.3.6]

• Paper: KnowPhish: Large Language Models Meet Multimodal Knowledge Graphs for Enhancing Reference-Based Phishing Detection
• Paper: KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents
• Paper: A Backpack Full of Skills: Egocentric Video Understanding with Diverse Task Perspectives
• Paper: Learning to Use Tools via Cooperative and Interactive Agents
• Paper: OPEx: A Component-Wise Analysis of LLM-Centric Agents in Embodied Instruction Following

[2024.3.5]

• Paper: RegionGPT: Towards Region Understanding Vision Language Model
• Paper: Beyond Specialization: Assessing the Capabilities of MLLMs in Age and Gender Estimation
• Paper: RIFF: Learning to Rephrase Inputs for Few-shot Fine-tuning of Language Models
• Paper: Non-autoregressive Sequence-to-Sequence Vision-Language Models
• Paper: Using LLMs for the Extraction and Normalization of Product Attribute Values

[2024.3.4]

• 🔥🔥🔥 Paper: Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models
• Paper: Tokenization counts: the impact of tokenization on arithmetic in frontier LLMs
• Paper: Chain-of-Thought Unfaithfulness as Disguised Accuracy
• Paper: LLMBind: A Unified Modality-Task Integration Framework
• Paper: Double-I Watermark: Protecting Model Copyright for LLM Fine-tuning
• Paper: Semantic Mirror Jailbreak: Genetic Algorithm Based Jailbreak Prompts Against Open-source LLMs

[2024.3.3]

• Paper: Meta-Task Prompting Elicits Embedding from Large Language Models
• Paper: Prompt-Driven Dynamic Object-Centric Learning for Single Domain Generalization
• Paper: LeMo-NADe: Multi-Parameter Neural Architecture Discovery with LLMs
• Paper: A Cognitive Evaluation Benchmark of Image Reasoning and Description for Large Vision Language Models
• Paper: VerifiNER: Verification-augmented NER via Knowledge-grounded Reasoning with Large Language Models

[2024.3.2]

• Paper: GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning
• Paper: Language Agents as Optimizable Graphs
• Paper: Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts
• Paper: OncoGPT: A Medical Conversational Model Tailored with Oncology Domain Expertise on a Large Language Model Meta-AI (LLaMA)
• Paper: Set the Clock: Temporal Alignment of Pretrained Language Models

[2024.3.1]

• Paper: Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers
• Paper: The All-Seeing Project V2: Towards General Relation Comprehension of the Open World
• Survey Paper: Retrieval-Augmented Generation for AI-Generated Content: A Survey
• Paper: Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models
• Paper: ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL

[2024.2.29]

• Paper: ShapeLLM: Universal 3D Object Understanding for Embodied Interaction
• Paper: The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
• Paper: Evaluating Very Long-Term Conversational Memory of LLM Agents
• Paper: Tower: An Open Multilingual Large Language Model for Translation-Related Tasks
• Paper: VRP-SAM: SAM with Visual Reference Prompt
• Paper: Securing Reliability: A Brief Overview on Enhancing In-Context Learning for Foundation Models

[2024.2.28]

• Survey Paper: Large Language Models for Data Annotation: A Survey
• Survey Paper: Investigating Cultural Alignment of Large Language Models
• Paper: AgentOhana: Design Unified Data and Training Pipeline for Effective Agent Learning
• Paper: LLMArena: Assessing Capabilities of Large Language Models in Dynamic Multi-Agent Environments
• Paper: Generative Pretrained Hierarchical Transformer for Time Series Forecasting
• Paper: Long-Context Language Modeling with Parallel Context Encoding
• Paper: GROUNDHOG: Grounding Large Language Models to Holistic Segmentation
• Paper: API-BLEND: A Comprehensive Corpora for Training and Benchmarking API LLMs

[2024.2.27]

• Survey Paper: A Survey on Knowledge Distillation of Large Language Models
• Mistral has released Mistral Large, with an MMLU rating second only to GPT-4, 32K contexts, no Chinese support, and API calls via La Plateforme and Azure.
  • Paper: Instruct-Imagen: Image Generation with Multi-modal Instruction

[2024.2.26]

• Paper: MoZIP: A Multilingual Benchmark to Evaluate Large Language Models in Intellectual Property

[2024.2.25]

• Paper: Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations

[2024.2.27]

• Mistral has released Mistral Large, with an MMLU rating second only to GPT-4, 32K contexts, no Chinese support, and API calls via La Plateforme and Azure.
• Paper: Instruct-Imagen: Image Generation with Multi-modal Instruction

[2024.2.26]

• Paper: MoZIP: A Multilingual Benchmark to Evaluate Large Language Models in Intellectual Property

[2024.2.25]

• Paper: Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations

[2024.2.24]

• Paper: ProLLaMA: A Protein Large Language Model for Multi-Task Protein Language Processing

[2024.2.23]

• Paper: Genie: Generative Interactive Environments

[2024.2.22]

• Paper: Video ReCap: Recursive Captioning of Hour-Long Videos

[2024.2.21]

• Paper: TOFUEVAL: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarization

[2024.2.20]

• Paper: Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive

[2024.2.19]

• Paper: How Easy is It to Fool Your Multimodal LLMs? An Empirical Analysis on Deceptive Prompts

[2024.2.18]

• Paper: Self-Play Fine-Tuning of Diffusion Models for Text-to-Image Generation

[2024.2.17]

• Paper: Chain-of-Thought Reasoning Without Prompting

[2024.2.16]

• 🔥🔥🔥SORA: Video generation models as world simulators

[2024.2.15]

• Paper: PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs
• Paper:VisualWebArena: EVALUATING MULTIMODAL AGENTS ON REALISTIC VISUAL WEB TASKS

[2024.2.14]

• Paper: Large Language Models for Autonomous Driving: Real-World Experiments

[2024.2.13]

• Paper: Feedback Loops With Language Models Drive In-Context Reward Hacking

[2024.2.12]

• 🔥🔥🔥The year of AI video generation exploded!

[2024.2.11]

• Paper: Large Language Model Meets Graph Neural Network in Knowledge Distillation

[2024.2.10]

• Paper: FACT-GPT: Fact-Checking Augmentation via Claim Matching with LLMs

[2024.2.9]

• Paper: Efficient Stagewise Pretraining via Progressive Subnetworks

[2024.2.8]

• Paper: On the Convergence of Zeroth-Order Federated Tuning in Large Language Models

[2024.2.7]

• Paper: SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models

[2024.2.6]

• Paper: How Well Can LLMs Negotiate? NEGOTIATIONARENA Platform and Analysis

[2024.2.5]

• Paper: PromptCrypt: Prompt Encryption for Secure Communication with Large Language Models

[2024.2.4]

• Paper: Evaluating Large Language Models for Generalization and Robustness via Data Compression

[2024.2.3]

• Paper: Can Large Language Models Understand Context?

[2024.2.2]

• Paper: Learning and Calibrating Heterogeneous Bounded Rational Market Behaviour with Multi-Agent Reinforcement Learning

[2024.2.1]

• Paper: Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners?

[2024.1.31]

• Paper: Binding Touch to Everything: Learning Unified Multimodal Tactile Representations

[2024.1.30]

• Paper: Scaling Sparse Fine-Tuning to Large Language Models

[2024.1.29]

• Paper: InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Models

[2024.1.28]

• Paper: Multimodal Pathway: Improve Transformers with Irrelevant Data from Other Modalities

[2024.1.27]

• Survey Paper: MM-LLMs: Recent Advances in MultiModal Large Language Models

[2024.1.26]

• Paper: ChipNeMo: Domain-Adapted LLMs for Chip Design

[2024.1.25]

• Paper: LMDrive: Closed-Loop End-to-End Driving with Large Language Models

[2024.1.24]

• Paper: MultiPLY: A Multisensory Object-Centric Embodied Large Language Model in 3D World

[2024.1.23]

• Yi Visual Language (Yi-VL) model is the open-source, multimodal version of the Yi Large Language Model (LLM) series, enabling content comprehension, recognition, and multi-round conversations about images.

[2024.1.22]

• Paper: Can Large Language Models Beat Wall Street? Unveiling the Potential of AI in Stock Selection

[2024.1.21]

• Paper: Beyond Reference-Based Metrics: Analyzing Behaviors of Open LLMs on Data-to-Text Generation

[2024.1.20]

• Paper: UPDP: A Unified Progressive Depth Pruner for CNN and Vision Transformer

[2024.1.19]

• Stability AI releases Stable Code 3B, a new code model that rivals the 7 billion Code Llama and can run without a GPU!

[2024.1.18]

• Paper: ChatQA: Building GPT-4 Level Conversational QA Models

[2024.1.17]

• Paper: Ask the experts: sourcing high-quality datasets for nutritional counselling through Human-AI collaboration

[2024.1.16]

• Paper: Machine Transla-on with Large Language Models: Prompt Engineering for Persian, English, and Russian Direc-ons

[2024.1.15]

• Paper: TOFU: A Task of Fictitious Unlearning for LLMs

[2024.1.14]

• Technical Report: DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models

[2024.1.13]

• GPT Store is now online!
• Paper: MagicVideo-V2: Multi-Stage High-Aesthetic Video Generation

[2024.1.12]

• Survey Paper: Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectives

[2024.1.11]

• Paper: Lyrics: Boosting Fine-grained Language-Vision Alignment and Comprehension via Semantic-aware Visual Objects

[2024.1.10]

• Paper: Incorporating Visual Experts to Resolve the Information Loss in Multimodal Large Language Models

[2024.1.9]

• Paper: Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding

[2024.1.8]

• Paper: WaveCoder: Widespread And Versatile Enhanced Instruction Tuning with Refined Data Generation

[2024.1.7]

• Paper: LLaMA Pro: Progressive LLaMA with Block Expansion

[2024.1.6]

• Paper: Task Oriented Dialogue as a Catalyst for Self-Supervised Automatic Speech Recognition

[2024.1.5]

• Paper: Learning to Prompt with Text Only Supervision for Vision-Language Models

[2024.1.4]

• Paper: LLM Augmented LLMs: Expanding Capabilities through Composition

[2024.1.3]

• Paper:CogAgent: A Visual Language Model for GUI Agents
• Paper: TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones

[2024.1.2]

• Paper:MobileVLM: A Fast, Strong and Open Vision Language Assistant for Mobile Devices

[2024.1.1]

• Paper:Generative AI for Math: Part I MATHPILE: A Billion-Token-Scale Pretraining Corpus for Math

2023

[2023.12.31]

• Hugging Face Year in Review: 2023, The Year of Open Source LLMs

[2023.12.30]

• Paper: Unsupervised embedding of trajectories captures the latent structure of scientific migration

[2023.12.29]

• KwaiAgents is a series of Agent-related works open-sourced by the KwaiKEG from Kuaishou Technology 【Paper/Github】

[2023.12.28]

• Paper: EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI
• Paper: Principled Instructions Are All You Need for Questioning LLaMA-1/2, GPT-3.5/4

[2023.12.27]

• Paper: The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction

[2023.12.26]

• Paper: LORAMOE: REVOLUTIONIZING MIXTURE OF EXPERTS FOR MAINTAINING WORLD KNOWLEDGE IN LANGUAGE MODEL ALIGNMENT

[2023.12.25]

• Survey Paper: Retrieval-Augmented Generation for Large Language Models: A Survey

[2023.12.24]

• Paper: Time is Encoded in the Weights of Finetuned Language Models

[2023.12.23]

• Paper: AppAgent: Multimodal Agents as Smartphone Users

[2023.12.22]

• Paper: A MATHEMATICAL PERSPECTIVE ON TRANSFORMERS

[2023.12.21]

• Paper: Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents

[2023.12.20]

• Paper: G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model

[2023.12.19]

• Paper: LLM360: Towards Fully Transparent Open-Source LLMs

[2023.12.18]

• Paper: Control Risk for Potential Misuse of Artificial Intelligence in Science

[2023.12.17]

• Paper: Mathematical discoveries from program search with large language models

[2023.12.16]

• 🔥🔥🔥Paper: Agent as Cerebrum, Controller as Cerebellum: Implementing an Embodied LMM-based Agent on Drones

[2023.12.15]

• Paper: Photorealistic Video Generation with Diffusion Models

[2023.12.14]

• Paper: LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios
• Paper: From Text to Motion: Grounding GPT-4 in a Humanoid Robot "Alter3"
• Paper: WonderJourney: Going from Anywhere to Everywhere

[2023.12.13]

• Paper: How to Convert Any Text Into a Graph of Concepts

[2023.12.12]

• Paper: LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models

[2023.12.11]

• Thesis from CMU (Carnegie Mellon University), Juncheng Billy Li: Towards Robust Large-scale Audio/Visual Learning

[2023.12.10]

• Survey Paper: Is Prompt All You Need? No. A Comprehensive and Broader View of Instruction Learning
• 🔥🔥🔥The first open source MoE Structure LLM is released!

[2023.12.9]

• Paper: Gemini: A Family of Highly Capable Multimodal Models

[2023.12.8]

• Paper: An Embodied Generalist Agent in 3D World

[2023.12.7]

• 🔥🔥🔥Gemini:The largest and most capable Google LLM is coming! Gemini Ultra, Gemini Pro, and Gemini Nano!

[2023.12.6]

• Paper: Minimizing Factual Inconsistency and Hallucination in Large Language Models

[2023.12.5]

• Paper: Mamba: Linear-Time Sequence Modeling with Selective State Spaces

[2023.12.4]

• Paper: Sequential Modeling Enables Scalable Learning for Large Vision Models

[2023.12.3]

• Paper: Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation

[2023.12.2]

• The PyTorch team has accelerated large model inference by a factor of 10, and with less than 1,000 lines of pure native PyTorch code!

[2023.12.1]

• Peking University's newest multimodal LLM open source: trained on mixed datasets and directly used for image-video tasks without modification: 【arXiv/Demo/GitHub/HuggingFace】

[2023.11.30]

• Paper: Learning skillful medium-range global weather forecasting

[2023.11.29]

• 🔥🔥🔥Text to Video, PIKA1.0 officially released!
• Paper: MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers

[2023.11.28]

• Break the Sequential Dependency of LLM Inference Using Lookahead Decoding

[2023.11.27]

• 🔥🔥🔥 Paper: White-Box Transformers via Sparse Rate Reduction: Compression Is All There Is?

[2023.11.26]

• Use vision to make Prompt! Xiangyang Shen demonstrates IDEA Research Institute's new model, no training or fine-tuning, out-of-the-box!

[2023.11.25]

• Paper:MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning

[2023.11.24]

• Paper: Social Motion Prediction with Cognitive Hierarchies

[2023.11.23]

• Paper: 3D-GPT: PROCEDURAL 3D MODELING WITH LARGE LANGUAGE MODELS.

[2023.11.22]

• Paper: Holographic codes from hyper invariant tensor networks

[2023.11.21]

• Paper: CAMEL: Communicative Agents for “Mind” Exploration of Large Language Model Society

[2023.11.20]

• Paper: Llemma: An Open Language Model For Mathematics

[2023.11.19]

• OpenAI Late Night Change, Sam Altman Kicked Out, Former CTO Temporary Interim CEO
• Paper: IN-CONTEXT LEARNING WITH ITERATIVE DEMON- STRATION SELECTION

[2023.11.18]

• Paper: EMU VIDEO: Factorizing Text-to-Video Generation by Explicit Image Conditioning

[2023.11.17]

• DeepMind's big model on Science: 1-minute prediction of 10 days of weather data, 90% of the indicators beyond the strongest human model
• Paper: Towards Verifiable Text Generation with Symbolic References

[2023.11.16]

• Microsoft's late-night amplification: GPT-4, DALL-E 3, GPTs for free, self-research big model dedicated AI chip
• DevOps finally has an exclusive big model, Ant and BYU jointly released

[2023.11.15]

• 🔥🔥🔥Paper: Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding
• 🔥🔥🔥Paper: SpectralGPT: Spectral Foundation Model
• Paper: CHATMAP : LARGE LANGUAGE MODEL INTERACTION WITH CARTOGRAPHIC DATA
• Paper: EviPrompt: A Training-Free Evidential Prompt Generation Method for Segment Anything Model in Medical Images

[2023.11.14]

• Paper: Can LLMs Follow Simple Rules?

[2023.11.13]

• Paper: Holistic Analysis of Hallucination in GPT-4V(ision): Bias and Interference Challenges

[2023.11.12]

• Paper: Ziya2: Data-centric Learning is All LLMs Need

[2023.11.11]

• Paper: PILL:Plug Into LLM with Adapter Expert and Attention Gat

[2023.11.10]

• Paper: Levels of AGI: Operationalizing Progress on the Path to AGI
• Paper: mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration

[2023.11.9]

• Paper: Pre-training LLMs using human-like development data corpus

[2023.11.8]

• Paper: TopicGPT: A Prompt-based Topic Modeling Framework

[2023.11.7]

• Paper: MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots

[2023.11.6]

• 🔥🔥🔥 01.Ai first open source large models, the Yi series of large models: Yi-34B and Yi-6B.
• 🔥🔥🔥 Elon Musk's xAI products in two consecutive releases: PromptIDE & Grok

[2023.11.5]

• Paper: GPT-Fathom: Benchmarking Large Language Models to Decipher the Evolutionary Path towards GPT-4 and Beyond

[2023.11.4]

• Paper: RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation

[2023.11.3]

• Paper: In-context Learning with Transformer Is Really Equivalent to a Contrastive Learning Pattern

[2023.11.2]

• DeepMind Exposes Next-Generation AlphaFold, Prediction Accuracy Skyrockets by Nearly 10 Percent! The AlphaFold moment for DNA and RNA is here!

[2023.11.1]

• NVIDIA releases ChipNeMo, a large model to design semiconductors and accelerate AI design chips
• Paper: LILO: Learning Interpretable Libraries by Compressing and Documenting Code

[2023.10.31]

• Paper: CodeFusion: A Pre-trained Diffusion Model for Code Generation

[2023.10.30]

• Paper: GraphGPT: Graph Instruction Tuning for Large Language Models

[2023.10.29]

• Paper: Creative Robot Tool Use with Large Language Models

[2023.10.28]

• Paper: Large Graph Models: A Perspective

[2023.10.27]

• Paper: SuperHF: Supervised Iterative Learning from Human Feedback

[2023.10.26]

• Paper: Woodpecker: Hallucination Correction for Multimodal Large Language Models

[2023.10.25]

• Paper: OpenAgents: An Open Platform for Language Agents in the Wild

[2023.10.24]

• Paper: Walking Down the Memory Maze: Beyond Context Limit through Interactive Reading

[2023.10.23]

• Paper: MusicAgent: An AI Agent for Music Understanding and Generation with Large Language Models
• Paper: Large Language Models Cannot Self-Correct Reasoning Yet

[2023.10.22]

• Paper: Uni3D: Exploring Unified 3D Representation at Scale

[2023.10.21]

• Paper: Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena

[2023.10.20]

• Paper: The Foundation Model Transparency Index
• Paper: XVAL: A CONTINUOUS NUMBER ENCODING FOR LARGE LANGUAGE MODELS

[2023.10.19]

• Paper: The Consensus Game: Language Model Generation via Equilibrium Search

[2023.10.18]

• Paper: SWE-bench: Can Language Models Resolve Real-World GitHub Issues?

[2023.10.17]

• Paper: Table-GPT: Table-tuned GPT for Diverse Table Tasks

[2023.10.16]

• Paper: MemGPT: Towards LLMs as Operating Systems

[2023.10.15]

• Paper: Think before you speak: Training Language Models With Pause Tokens

[2023.10.14]

• Paper: How FaR Are Large Language Models From Agents with Theory-of-Mind?

[2023.10.13]

• Paper: Ferret: Refer and Ground Anything Anywhere at Any Granularity

[2023.10.12]

• Paper: Understanding the Effects of RLHF on LLM Generalisation and Diversity
• Paper: Learning Interactive Real-World Simulators

[2023.10.11]

• Paper: PB-LLM: Partially Binarized Large Language Models

[2023.10.10]

• Paper: MVDREAM:MULTI-VIEW DIFFUSION FOR 3D GENERATION

[2023.10.9]

• Paper: MiniGPT-5: Interleaved Vision-and-Language Generation via Generative Vokens

[2023.10.8]

• Paper: Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes

[2023.10.7]

• Survey Paper: A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future

[2023.10.6]

• Paper: Language Models Represent Space and Time

[2023.10.5]

• Paper: Adapting Large Language Models via Reading Comprehension

[2023.10.4]

• Paper: LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models

[2023.10.3]

• Paper: CHAIN-OF-VERIFICATION REDUCES HALLUCINATION IN LARGE LANGUAGE MODELS

[2023.10.2]

• Paper: DreamLLM: Synergistic Multimodal Comprehension and Creation

[2023.10.1]

• Paper: Investigating the Catastrophic Forgetting in Multimodal Large Language Models

[2023.9.30]

• Paper: Cumulative Reasoning with Large Language Models

[2023.9.29]

• Paper: Investigating the Catastrophic Forgetting in Multimodal Large Language Models

[2023.9.28]

• Survey Paper: Instruction Tuning for Large Language Models: A Survey

[2023.9.27]

• Chinese LLaMA-2 tops the list, open source and commercially available! With a budget of one thousand yuan, training for half a day, the effect is comparable to mainstream large models.
• Lingxin Intelligence releases CharacterGLM: Play AI role-playing, 6B model is now open source.
• Paper: Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement

[2023.9.26]

• The biggest bug of the large model! The accuracy of the answers is almost zero, from GPT to Llama, none are spared: Paper:The Reversal Curse: LLMs trained on “A is B” fail to learn “B is A”
• Paper: Chain-of-Verification Reduces Hallucination in Large Language Models
• Paper: Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models

[2023.9.25]

• Paper: Cell2Sentence: Teaching Large Language Models the Language of Biology

[2023.9.24]

• Writer model is open source, commercially available, and there are a total of 8 models.
• Paper: LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models

[2023.9.23]

• Defeat GPT-4? 70 billion parameter Xwin-LM climbs up to the top of Stanford AlpacaEval
• Paper: End-to-End Speech Recognition Contextualization with Large Language Models

[2023.9.22]

• AgentVerse: A Framework for Multi-LLM Environment Simulation
• The performance of the 20 billion scale large model is comparable to Llama2-70B! It is completely open source, and everything from the base to the tools is well arranged.
• Paper: Kosmos-2.5: A Multimodal Literate Model

[2023.9.21]

• 34B parameter exceeds GPT-4! "Mathematical Universal Large Model" MAmmoTH open source: average accuracy rate increased by 29% (Paper/Project Page)
• Paper: Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions

[2023.9.20]

• Optimizing LLMs from a Dataset Perspective
• Google DeepMind predicts 71 million genetic mutations, decrypts the human genetic code, and is now published in Science. It has been open-sourced.(Paper/Science/Dataset)
• Paper: Replacing softmax with ReLU in Vision Transformers

[2023.9.19]

• Paper: NExT-GPT: Any-to-Any Multimodal LLM

[2023.9.18]

• Survey Paper: The Rise and Potential of Large Language Model Based Agents: A Survey

[2023.9.17]

• Paper: Textbooks Are All You Need II: phi-1.5 technical report

[2023.9.16]

• Paper: DOLA: DECODING BY CONTRASTING LAYERS IMPROVES FACTUALITY IN LARGE LANGUAGE MODELS

[2023.9.15]

• Microsoft Open Sources EvoDiff: A New Generation of Protein Generative AI : [Paper]
• Paper: DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning

[2023.9.14]

• Can LLMs Really Reason and Plan? | blog @ CACM | Communications of the ACM【Paper/Video】

[2023.9.13]

• Chinese multimodal large model VisCPM open API interface! The upgraded version is far more capable than similar models(Paper/Github)
• Survey Paper: A Survey on Large Language Model based Autonomous Agents

[2023.9.12]

• Paper: From Sparse to Dense: GPT-4 Summarization with Chain of Density Prompting

[2023.9.11]

• Paper:Narrator: Towards Natural Control of Human-Scene Interaction Generation via Relationship Reasoning

[2023.9.10]

• Survey Paper: Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models

[2023.9.9]

• Open-source version of code interpreter tops GitHub hotlist, runs locally, accesses Internet: [Github]
• Peking University propose the Structured Chain of Thought SCoT: [Paper]
• Paper:LARGE LANGUAGE MODELS AS OPTIMIZERS
• Survey Paper:RenAIssance: A Survey into AI Text-to-Image Generation in the Era of Large Model

[2023.9.8]

• Paper:Physically Grounded Vision-Language Models for Robotic Manipulation

[2023.9.7]

• Baichuan Intelligence Releases Baichuan2 Big Model: Comprehensively Ahead of Llama2, Training Slices Also Open Source: Github/Technical Report

[2023.9.6]

• Paper: TouchStone: Evaluating Vision-Language Models by Language Models

[2023.9.5]

• 70 billion parameters Llama 2 training accelerated 195%! Training/fine-tuning/reasoning full-process program open source, 0 code one-stop solution!

• Survey Paper:Large language models in medicine: the potentials and pitfalls

[2023.9.4]

• Paper:SeqGPT: An Out-of-the-box Large Language Model for Open Domain Sequence Understanding

[2023.9.3]

• Paper:PE-MED: Prompt Enhancement for Interactive Medical Image Segmentation

[2023.9.2]

• Paper: SkipcrossNets: Adaptive Skip-cross Fusion for Road Detection

[2023.9.1]

• 8 LLM products are fully open to the whole community, including IOS and Android APP【Baidu, 百川智能, SenseChat, 智谱清言, ByteDance, INTERN, CAS, MiniMax】
• Paper:FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer

[2023.8.31]

• Paper:FLatten Transformer: Vision Transformer using Focused Linear Attention

[2023.8.30]

• Paper: SeamlessM4T—Massively Multilingual & Multimodal Machine Translation

[2023.8.29]

• Paper:Giraffe: Adventures in Expanding Context Lengths in LLMs

[2023.8.28]

• Paper:ExpeL: LLM Agents Are Experiential Learners

[2023.8.27]

• Paper:OVO: One-shot Vision Transformer Search with Online distillation

[2023.8.26]

• WizardLM: Open-source! [demo / HuggingFace / github]

[2023.8.25]

• Paper:Safe Reinforcement Learning via Probabilistic Logic

[2023.8.24]

• Paper:Giraffe: Adventures in Expanding Context Lengths in LLMs

• Paper:Graph of Thoughts: Solving Elaborate Problems with Large Language Models

[2023.8.23]

• HuggingFace Introducing IDEFICS: An Open Reproduction of State-of-the-Art Visual Language Model
• Paper:SeamlessM4T—Massively Multilingual & Multimodal Machine Translation

[2023.8.22]

• Paper:RoboAgent:Generalization and Efficiency in Robot Manipulation via Semantic Augmentations and Action Chunking

[2023.8.21]

• Paper:VisIT-Bench: A Benchmark for Vision-Language Instruction Following Inspired by Real-World Use
• Paper:Exploring the Intersection of Large Language Models and Agent-Based Modeling via Prompt Engineering

[2023.8.20]

• Paper:DiffRate : Differentiable Compression Rate for Efficient Vision Transformers

[2023.8.19]

• WizardMath: model checkpoints / project page / Paper

[2023.8.18]

• Paper:Shepherd: A Critic for Language Model Generation

[2023.8.17]

• Paper:Prompt Switch: Efficient CLIP Adaptation for Text-Video Retrieval

[2023.8.16]

• Paper:The Devil is in the Errors: Leveraging Large Language Models for Fine-grained Machine Translation Evaluation

[2023.8.15]

• Paper:Self-Alignment with Instruction Backtranslation

[2023.8.14]

• Paper:VideoFactory: Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation

[2023.8.13]

• Paper:SMILE: Single-turn to Multi-turn Inclusive Language Expansion via ChatGPT for Mental Health Support' qiuhuachuan

[2023.8.12]

• Paper:Pre-Trained Large Language Models for Industrial Control

[2023.8.11]

• Paper:Accelerating LLM Inference with Staged Speculative Decoding

[2023.8.10]

• Paper:Foundational Models Defining a New Era in Vision: A Survey and Outlook

[2023.8.9]

• Stability AI has just announced the release of StableCode, its very first LLM generative AI product for coding
• Paper:Seeing through the Brain: Image Reconstruction of Visual Perception from Human Brain Signals

[2023.8.8]

• Paper:AgentBench: Evaluating LLMs as Agents

[2023.8.7]

• Paper:SmartMoE: Efficiently Training Sparsely-Activated Models through Combining Offline and Online Parallelization

[2023.8.6]

• Paper: UniVTG: Towards Unified Video-Language Temporal Grounding

[2023.8.5]

• Paper: Universal and Transferable Adversarial Attacks on Aligned Language Models

[2023.8.4]

• Chinese LLaMA2 model is open source and commercially usable
• Paper:Scientific discovery in the age of artificial intelligence

[2023.8.3]

• Paper: Scaling Data Generation in Vision-and-Language Navigation

[2023.8.2]

• Paper: AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?

[2023.8.1]

• Paper:Robust Distortion-free Watermarks for Language Models

[2023.7.31]

• Paper: Foundational Models Defining a New Era in Vision: A Survey and Outlook

[2023.7.30]

• Paper: Challenges and Applications of Large Language Models

[2023.7.29]

• Paper: A Watermark for Large Language Models

[2023.7.28]

• Paper:Med-Flamingo: a Multimodal Medical Few-shot Learner

[2023.7.27]

• Paper: using Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs

[2023.7.26]

• Paper:3D-LLM: Injecting the 3D World into Large Language Models

[2023.7.25]

• Paper:ChatSpot: Bootstrapping Multimodal LLMs via Precise Referring Instruction Tuning

[2023.7.24]

• Paper:Zero-1-to-3: Zero-shot One Image to 3D Object

[2023.7.23]

• ChatGPT based on Android, pre-register location

• Paper:OBJECT 3DIT: Language-guided 3D-aware Image Editing

[2023.7.22]

• Paper:Brain2Music: Reconstructing Music from Human Brain Activity

[2023.7.21]

• Paper:A Survey on Evaluation of Large Language Models

[2023.7.20]

• New Architecture: RetNetwork, beyond Transformer 👉Paper👈

[2023.7.19]

• Meta releases LLAMA 2, open source and commercially available.

[2023.7.18]

• Paper:Learning to Retrieve In-Context Examples for Large Language Models

[2023.7.17]

• Paper:HyperDreamBooth: HyperNetworks for Fast Personalization of Text-to-Image Models

[2023.7.16]

• Emu model is open source, a versatile expert in 'multimodal to multimodal': Model / Demo

[2023.7.15]

• Paper:Self-consistency for open-ended generations

[2023.7.14]

• Paper:Patch n’ Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution

[2023.7.13]

• Paper:Large language models encode clinical knowledge

[2023.7.12]

• Claude2👉 [Paper]Model Card and Evaluations for Claude Models / [Website](https://claude.ai/)

[2023.7.11]

• Paper: VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models
• Paper: Focused Transformer: Contrastive Training for Context Scaling

[2023.7.10]

• Paper:Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models

[2023.7.9]

• Paper: Schema-learning and rebinding as mechanisms of in-context learning and emergence

[2023.7.8]

• Paper:SPAE: Semantic Pyramid AutoEncoder for Multimodal Generation with Frozen LLMs

[2023.7.7]

• GPT-4 API general availability
• Paper:Jailbroken: How Does LLM Safety Training Fail?

[2023.7.6]

• Paper:LONGNET: Scaling Transformers to 1,000,000,000 Tokens

[2023.7.5]

• MetaGPT: Multi-Role Meta-Programming Framework
• Paper: Conformer LLMs -- Convolution Augmented Large Language Models

[2023.7.4]

• Paper:Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic

[2023.7.3]

• Largest-scale Chinese multitask instruction set, introducing a thousand Chinese datasets.

[2023.7.2]

• Paper: Towards Measuring the Representation of Subjective Global Opinions in Language Models

[2023.7.1]

• Paper:Masked Vision-language Transformer in Fashion

[2023.6.30]

• Paper: Inferring the Goals of Communicating Agents from Actions and Instructions

[2023.6.29]

• Paper: AudioPaLM: A Large Language Model That Can Speak and Listen

[2023.6.28]

• Paper:Kosmos-2: Grounding Multimodal Large Language Models to the World

[2023.6.27]

• Paper: A Survey on Multimodal Large Language Models

[2023.6.26]

• Paper: PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Finance

[2023.6.25]

• Paper: LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion

[2023.6.24]

• Paper: PromptIR: Prompting for All-in-One Blind Image Restoration

[2023.6.23]

• Paper: OphGLM: Training an Ophthalmology Large Language-and-Vision Assistant based on Instructions and Dialogue

[2023.6.22]

• Stanford has released an automatic evaluation system for LLM called AlpacaEval
• Ocean-1: the world's first contact center foundation model.

[2023.6.21]

• GPT-Engineering, Who generates an entire codebase based on a prompt.

[2023.6.20]

• Paper: Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale

[2023.6.19]

• Technical Report: AIGC industry overview article from SEALAND SECURITIES

[2023.6.18]

• Paper: ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory

[2023.6.17]

• Paper: Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and Text Integration

[2023.6.16]

• Financial FinGPT model open source, benchmarked against BloombergGPT, training parameters can be reduced from 6.17 billion to 3.67 million, can predict stock prices. (Paper/Code)

[2023.6.15]

• Paper:MetaVL: Transferring In-Context Learning Ability From Language Models to Vision-Language Models

[2023.6.14]

• Paper:XrayGPT: Chest Radiographs Summarization using Medical Vision-Language Models

[2023.6.13]

• Paper:Simple and Controllable Music Generation

[2023.6.12]

• Paper: MIMIC-IT: Multi-Modal In-Context Instruction Tuning

[2023.6.11]

• Paper: M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models

[2023.6.10]

• Aquila, language model series, including the Aquila Basic Model (7B and 33B), AquilaChat dialogue model, and AquilaCode text-to-code generation model.

[2023.6.9]

• Paper: Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding

[2023.6.8]

• Paper: FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance

[2023.6.7]

• Paper: XPhoneBERT: A Pre-trained Multilingual Model for Phoneme Representations for Text-to-Speech

[2023.6.6]

• Paper: XuanYuan 2.0: A Large Chinese Financial Chat Model with Hundreds of Billions Parameters
• Paper: UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild

[2023.6.5]

• Paper: Controllable Text-to-Image Generation with GPT-4

[2023.6.4]

• PandaGPT: One model unifies six modalities(Page/Paper)

[2023.6.3]

• Paper: Direct Preference Optimization:Your Language Model is Secretly a Reward Model

[2023.6.2]

• Paper: SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks

[2023.6.1]

• Paper: Generating Images with Multimodal Language Models

[2023.5.31]

• Intel announces the Aurora genAI, which is generative AI model with 1 trillion parameters

• HuotuoGPT, towards Taming Language Model to Be a Doctor(Github/Demo/Paper)

• Paper: Large Language Models Meet NL2Code: A Survey

[2023.5.30]

• Paper: Large Language Models as Tool Makers

• Paper: BiomedGPT: A Unified and Generalist Biomedical Generative Pre-trained Transformer for Vision, Language, and Multimodal Tasks

• Paper: OlaGPT: Empowering LLMs With Human-like Problem-Solving Abilities

[2023.5.29]

• Falcon: based on the 1 trillion token open-source large model, surpassing 65 billion LLaMA, commercially available.

• ToolBench: the open platform for large language models used for training, service, and evaluation of tool learning

• Paper: EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought

[2023.5.28]

• Paper: ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation
• Paper:RecurrentGPT: Interactive Generation of (Arbitrarily) Long Text

[2023.5.27]

• Paper: Gorilla: Large Language Model Connected with Massive APIs

• Paper: ChatCAD+: Towards a Universal and Reliable Interactive CAD using LLMs

• Paper: BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing

[2023.5.26]

• Paper: Iterative Forward Tuning Boosts In-context Learning in Language Models

[2023.5.25]

• Paper: Diversity-Aware Meta Visual Prompting

[2023.5.24]

• Paper:VideoLLM: Modeling Video Sequence with Large Language Models

[2023.5.23]

• Paper:Symbol tuning improves in-context learning in language models
• Paper: PointGPT: Auto-regressively GenerativePre-training from Point Clouds

[2023.5.22]

• Paper: Searching for Needles in a Haystack: On the Role of Incidental Bilingualism in PaLM's Translation Capability

[2023.5.21]

• Paper:Language Models Meet World Models: Embodied Experiences Enhance Language Models

[2023.5.20]

• Paper:AttentionViz: A Global View of Transformer Attention

[2023.5.19]

• OpenAI introducing the ChatGPT APP for IOS
• Paper: VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks

[2023.5.18]

• Paper: StructGPT: A General Framework for Large Language Model to Reason over Structured Data

[2023.5.17]

• Paper: Interpretability at Scale: Identifying Causal Mechanisms in Alpaca

[2023.5.16]

• Paper:MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers

[2023.5.15]

• Paper: ArtGPT-4: Artistic Vision-Language Understanding with Adapter-enhanced MiniGPT-4

[2023.5.14]

• Paper: Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes

[2023.5.13]

• Paper: VPGTrans: Transfer Visual Prompt Generator across LLMs

[2023.5.12]

• Paper: Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?

[2023.5.11]

• Google has released PaLM 2, which improves multiple abilities and offers four versions for selection. (Paper/Page)

• The open-source healthcare large language model NHS-LLM and OpenGPT.

• Paper: Language models can explain neurons in language models

[2023.5.10]

• DetGPT: Detect What You Need via Reasoning (Code/Demo)

• Meta releases a large-scale model called ImageBind that can traverse six senses, and it is now open-source. (Paper/Code)

• HuoTuo: Open Source Chinese Medical Large Model of Harbin Institute of Technology

• Paper: X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages

[2023.5.9]

• Paper: Transfer Visual Prompt Generator across LLMs 【Code】

[2023.5.8]

• PandaLM: the first large model for automated evaluation.(Code)

• Paper:AutoML-GPT: Automatic Machine Learning with GPT

[2023.5.7]

• Paper: Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision

[2023.5.6]

• IFLYTEK officially releases the LLM named SparkDesk

• OpenAI release the language-to-3D model: Shape.E (Paper/Project Page)

• Paper: Search-in-the-Chain: Towards the Accurate, Credible and Traceable Content Generation for Complex Knowledge-intensive Tasks

[2023.5.5]

• Paper: Don't Stop Pretraining? Make Prompt-based Fine-tuning Powerful Learner

[2023.5.4]

• Paper: Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes

[2023.5.3]

• Paper:Transfer Visual Prompt Generator across LLMs

[2023.5.2]

• Customize your own LLMs, stop prompt-tunning: Lamini

• Paper: Unlimiformer: Long-Range Transformers with Unlimited Length Input

[2023.5.1]

• Paper: mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality

[2023.4.30]

• Paper: Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond

[2023.4.29]

• Paper: LLM+P: Empowering Large Language Models with Optimal Planning Proficiency

[2023.4.28]

• Paper: Unleashing Infinite-Length Input Capacity for Large-scale Language Models with Self-Controlled Memory System

[2023.4.27]

• AudioGPT: [Project Page/Paper]

• Paper:Answering Questions by Meta-Reasoning over Multiple Chains of Thought

[2023.4.26]

• Paper: WizardLM: Empowering Large Language Models to Follow Complex Instructions

[2023.4.25]

• Google releases the Security AI workbench

• Paper: Enhancing Chain-of-Thoughts Prompting with Iterative Bootstrapping in Large Language Models

[2023.4.24]

• Paper: Improving Grounded Language Understanding in a Collaborative Environment by Interacting with Agents Through Help Feedback

[2023.4.23]

• Paper: Emergent and Predictable Memorization in Large Language Models

[2023.4.22] Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models [Paper/Project]

[2023.4.21]

• Paper:

  Progressive-Hint Prompting Improves Reasoning in Large Language Models

  Pretrained Language Models as Visual Planners for Human Assistance

[2023.4.20]

• Google DeepMind: Bringing together two world-class AI teams

• Paper: Visual Instruction Tuning

[2023.4.19]

• Paper: Towards Robust Prompts on Vision-Language Models

[2023.4.18]

• HuaTuo:Tunning LLaMA Model with chinese medical instructions

• MiniGPT-4 [Project Page/Paper]

• Paper: Multimodal C4: An Open, Billion-scale Corpus of Images Interleaved With Text

[2023.4.17]

• The open source democratizes large language models,OpenAssistant, supports 35 languages, and can use RLHF data for free[Project Page/Code/Paper]

• Paper: Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition

[2023.4.16]

• Paper: AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models

[2023.4.15]

• Paper: CAMEL: Communicative Agents for "Mind" Exploration of Large Scale Language Model Society

• Visual Med-Alpaca: Bridging Modalities in Biomedical Language Models

[2023.4.14]

• Amazon announcing new tools for building with Generative AI

• Paper: ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learning

[2023.4.13] Three Amazing Works:

• AutoGPT: An Autonomous GPT-4 Experiment 👉Code👈

• Databricks releases Dolly 2.0, the first open, instruction-following LLM for commercial use

• Microsoft released the DeepSpeed Chat: Own your ChatGPT

[2023.4.12] OpenAGI: When LLM Meets Domain Experts

[2023.4.11] Why think step-by-step? Reasoning emerges from the locality of experience

[2023.4.10] TagGPT: Large Language Models are Zero-shot Multimodal Taggers

[2023.4.9] A new AI model from Meta AI: Segment Anything Model (SAM) (Paper/Code)

[2023.4.8] EleutherAI&Yale et al. proposed a large-scale language model analysis suite that spans training and extension: Pythia (Paper/Code)

[2023.4.7] Stanford releases the 7 billion parameter open-source model Vicuna-7B, which is compact, efficient, but powerful in functionality

[2023.4.6] Effective Theory of Transformers at Initialization

[2023.4.5] REFINER: Reasoning Feedback on Intermediate Representations

[2023.4.4] Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?

[2023.4.3] Self-Refine: Iterative Refinement with Self-Feedback

[2023.4.1] A survey of Large Language Models

[2023.3.31] BloombergGPT: A Large Language Model for Finance

[2023.3.30] GPTEval: NLG Evaluation using GPT-4 with Better Human Alignment

[2023.3.29] LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention

[2023.3.28] ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks

[2023.3.27] Scaling Expert Language Models with Unsupervised Domain Discovery

[2023.3.26] CoLT5: Faster Long-Range Transformers with Conditional Computation

[2023.3.23] OpenAI announces 'Plug-ins' for ChatGPT that enable it to perform actions beyond text.

[2023.3.22] GitHub launches Copilot X, aiming at the future of AI-powered software development.

[2023.3.21] Google Bard is now available in the US and UK, w/ more countries to come.

[2023.3.20] OpenAI’s new paper looks at the economical impact of LLMs+Labor Market.GPTs are GPTs: An Early Look at the Labor Market Impact Potential of Large Language Models

[2023.3.17] Microsoft 365 Copilot released. Word, Excel, PowerPoint, Outlook powered by LLMs.

[2023.3.16] Baidu announcing the LLM named "文心一言"(ERNIE3.0 + PLATO)

[2023.3.15] Two Breaking News: - Announcing GPT4 by OpenAI from Microsoft. Paper🔗 - Announcing PaLM API by Google.

[2023.3.13] LLaMA has been fine-tuned by Stanford

[2023.3.10] Announcing OpenChatKit by Together

[2023.3.9] GPT-4 is coming next week and it will be multimodal,announced by OpenAI.

[2023.3.8] Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models

[2023.3.7] Larger language models do in-context learning differently

[2023.3.6] Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning