Awesome Fine-Grained Multimodal Perception

A curated collection of the latest research and resources on Fine-Grained Multimodal Perception. This repository encompasses datasets, benchmarks, research papers, and practical methods for enhancing fine-grained perception capabilities in Multimodal Large Language Models (MLLMs).

🚀🚀🚀 Contributions are welcome! If you find any missing papers, datasets, or tools, feel free to open an issue or submit a pull request.

---

📢 Latest Updates

Date	News
2026-06-04	Added Attentive-CoT and Beyond Visual Memory to Training-Based Methods (SFT & Distillation)
2026-06-03	Updated iVGR venue to ICML 2026; Reorganized structure with What is, 📚 TOC, and time-based sorting

📜 View More Updates

Date	News

---

What is Fine-Grained Multimodal Perception?

Multimodal Large Language Models (MLLMs) excel at broad visual understanding but still struggle with fine-grained perception, where decisive evidence is small and easily overwhelmed by global context. Recent advancements have shifted towards a "Thinking-with-Images" paradigm, where MLLMs actively acquire local information during inference rather than relying solely on a global image encoding.

This awesome list categorizes methods into four paradigms:

• Data-Centric Methods: Improving perception through data quality, quantity, and synthetic generation
• Training-Free Methods: Enhancing perception at inference time via prompting, chain-of-thought, and attention strategies
• Agentic: Thinking with Images: Actively interacting with images through tools (zoom, crop, search, edit) during inference
• Training-Based Methods: Improving perception through supervised fine-tuning, distillation, and reinforcement learning

⬆ Back to Top

---

📚 Table of Contents

• 📢 Latest Updates
• What is Fine-Grained Multimodal Perception?
• Benchmarks & Datasets
• Research Papers
  • Data-Centric Methods
  • Training-Free Methods
  • Agentic: Thinking with Images
  • Training-Based Methods
    • Supervised Fine-Tuning & Distillation
    • Reinforcement Learning
• Applications & Domains
• Why We Do It
• Contact Us
• Star History

---

Benchmarks & Datasets

Task Legend: FG: Fine-Grained Perception | OCR: Text Recognition | Cnt: Counting | Grd: Grounding | Rea: Reasoning

Benchmark	Paper	Venue & Year	Task	Highlights	Download
Preprints
GeoBrowse	GeoBrowse: A Geolocation Benchmark for Agentic Tool Use with Expert-Annotated Reasoning Traces	Arxiv 2026	FG, Rea	Geolocation benchmark, agentic tool use, expert reasoning traces	GitHub
CountQA	CountQA: How Well Do MLLMs Count in the Wild?	Arxiv 2025	Cnt	Visual counting with reasoning	HuggingFace
CoCoT	CoCoT: Contrastive Chain-of-Thought Prompting for Large Multimodal Models with Multiple Image Inputs	Arxiv 2024	Grd	Visual grounding with reasoning	N/A
Rexverse	ChatRex: Taming Multimodal LLM for Joint Perception and Understanding	Arxiv 2024	FG	Fine-grained visual understanding	GitHub
2026
VisuRiddles	VisuRiddles: Fine-grained Perception is a Primary Bottleneck for Multimodal Large Language Models in Abstract Visual Reasoning	AAAI 2026	FG	Visual riddles, fine-grained perception evaluation	Github
GroundingME	GroundingME: Grounding Multi-Modal Evaluation	CVPR 2026	Grd	Multi-modal grounding evaluation	GitHub
RTV-Bench	RTV-Bench: Benchmarking MLLM Continuous Perception	ICLR 2026	FG, Rea	Real-time video analysis, 552 videos, 4,608 QA pairs, multi-timestamp reasoning	GitHub
SFE	Scientists' First Exam: Probing Cognitive Abilities of MLLM via Perception, Understanding, and Reasoning	ICLR 2026	FG, Rea	Scientific cognitive evaluation, three interconnected levels	GitHub
Thyme-SFT/RL	Thyme: Thinking with Images for Visual Reasoning	ICLR 2026	FG, Rea	Visual reasoning with tool use	GitHub
Visual Probe	Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search	ICLR 2026	FG	Visual probing for perception	GitHub
TreeBench	Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodology	ICLR 2026	Rea	Traceable reasoning evaluation	GitHub
ZoomBench	Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception	ICML 2026	FG, Rea	845 VQA samples, 6 perceptual dimensions, dual-view evaluation	GitHub
2025
HR-Bench	Divide and Conquer: A Comprehensive Benchmark for High-Resolution Image Understanding	AAAI 2025	FG	High-resolution image understanding	GitHub
MME-RealWorld	MME-RealWorld: Evaluating Real-World Perception in MLLMs	ICLR 2025	FG, Grd	Real-world perception benchmark	GitHub
ColorBench	ColorBench: Can VLMs See and Understand the Colorful World? A Benchmark for Color Perception	NeurIPS 2025	FG	Color perception evaluation	GitHub
2024
VStar	V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs	CVPR 2024	FG	Visual search, attribute recognition	GitHub
CV-Bench	Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs	CVPR 2024	FG, Rea	Computer vision-centric benchmark	HuggingFace
MMVP	Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs	CVPR 2024	FG	Visual shortcomings evaluation	GitHub
2017
Visual Genome	Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations	IJCV 2017	Grd, FG	Dense image annotations, grounding	HuggingFace

⬆ Back to Top

---

Research Papers

Data-Centric Methods

This category focuses on methods that improve fine-grained perception through data quality, quantity, and synthetic data generation pipelines.

Title	Venue & Year	Highlights/Keywords	Code
2025
MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct	ACL 2025	Evolution, Instruction Tuning	GitHub
Oasis: One Image is All You Need for Multimodal Instruction Data Synthesis	ICCV 2025	Autonomous Synthesis, Open-source	GitHub
First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-Training	NeurIPS 2025	Unsupervised Pre-training	GitHub
Hallucination at a Glance: Controlled Visual Edits and Fine-Grained Multimodal Learning	NeurIPS 2025	Minimally Edited, Difference Detection	GitHub
2024
Genixer: Empowering Multimodal Large Language Models as a Powerful Data Generator	ECCV 2024	VQA Generation, Unlabeled Images	GitHub
Multimodal Self-Instruct: Synthetic Abstract Image and Visual Reasoning Instruction Using Language Model	EMNLP 2024	Self-Instruct, Synthetic Data	GitHub

⬆ Back to Top

---

Training-Free Methods

This category covers inference-time approaches that enhance fine-grained perception without additional training, leveraging prompting strategies, chain-of-thought reasoning, and attention mechanisms.

Title	Venue & Year	Highlights/Keywords	Code
Preprints
Q-Zoom: Query-Aware Adaptive Perception for Efficient Multimodal Large Language Models	Arxiv 2026	Query-Aware, Adaptive Perception, Efficient Zoom	Github
See It, Say It, Sorted: An Iterative Training-Free Framework for Visually-Grounded Multimodal Reasoning in LVLMs	Arxiv 2026	Training-Free, Iterative, Visually-Grounded Reasoning	GitHub
SvfEye: A Semantic-Visual Fusion Framework with Multi-Scale Visual Context for Multimodal Reasoning	Arxiv 2026	Semantic-Visual Fusion, Multi-Scale Context	GitHub
Adaptive Chain-of-Focus Reasoning via Dynamic Visual Search and Zooming for Efficient VLMs	Arxiv 2025	Focusing Strategy, Chain Reasoning	GitHub
Socratic Questioning: Learn to Self-guide Multimodal Reasoning in the Wild	Arxiv 2025	Self-guided Reasoning, Socratic Method	GitHub
Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Models	Arxiv 2024	Image-of-Thought, Reasoning Refinement	N/A
Chain of Thought Prompt Tuning in Vision Language Models	Arxiv 2023	Prompt Tuning, VLM CoT	N/A
Visual Chain of Thought: Bridging Logical Gaps with Multimodal Infillings	Arxiv 2023	Multimodal Infillings, Visual CoT	GitHub
2026
ERGO: Efficient High-Resolution Visual Understanding for Vision-Language Models	ICLR 2026	Efficient High-Resolution, Visual Understanding	GitHub
Hide: Rethinking the zoom-in method in high resolution mllms via hierarchical decoupling	ICML 2026	Attention-based Detection	GitHub
2025
ZoomEye: Enhancing Multimodal LLMs with Human-Like Zooming Capabilities through Tree-Based Search	EMNLP 2025	Tree Search, Attention Mapping	GitHub
Imagine while Reasoning in Space: Multimodal Visualization-of-Thought	ICML 2025	Spatial Visualization, Imaginative Reasoning	GitHub
2024
KAM-CoT: Knowledge Augmented Multimodal Chain-of-Thoughts Reasoning	AAAI 2024	Knowledge Augmentation, CoT Reasoning	N/A
Visual Chain-of-Thought Prompting for Knowledge-based Visual Reasoning	AAAI 2024	Interactive Prompting, Knowledge-based Reasoning	N/A
TextCoT: Zoom In for Enhanced Multimodal Text-Rich Image Understanding	ACM TOMM	Text-rich Images, Zoom-in Strategy	GitHub
Compositional Chain-of-Thought Prompting for Large Multimodal Models	CVPR 2024	Compositional Prompting	GitHub
Cantor: Inspiring Multimodal Chain-of-Thought of MLLM	MM 2024	CoT Inspiration, MLLM Reasoning	GitHub
Mind's Eye of LLMs: Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models	NeurIPS 2024	Visualization-of-Thought, Spatial Reasoning	GitHub
Multimodal Chain-of-Thought Reasoning in Language Models	TMLR 2024	Multimodal CoT, Two-stage Framework	GitHub
2023
Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models	NeurIPS 2023	Compositional Reasoning, Tool Integration	GitHub

⬆ Back to Top

---

Agentic: Thinking with Images

This category includes models that actively interact with images during inference using tools (zoom, crop, search, edit, sketch), enabling iterative visual exploration and dynamic focus on regions of interest. These methods reduce interference by isolating micro-crops but typically incur higher latency due to multi-pass inference.

Title	Venue & Year	Highlights/Keywords	Code
Preprints
S1-VL: Scientific Multimodal Reasoning Model with Thinking-with-Images	Arxiv 2026	Scientific Reasoning, Thinking-with-Images	N/A
Test-time Scaling over Perception: Resolving the Grounding Paradox in Thinking with Images	Arxiv 2026	Test-time Scaling, Grounding Paradox	N/A
Walk the Talk: Bridging the Reasoning-Action Gap for Thinking with Images via Multimodal Agentic Policy Optimization	Arxiv 2026	Agentic Policy Optimization, Reasoning-Action Gap	N/A
CodeDance: A Dynamic Tool-integrated MLLM for Executable Visual Reasoning	Arxiv 2025	Tool-integrated, Executable Visual Reasoning	GitHub
DeepEyesV2: Toward Agentic Multimodal Model	Arxiv 2025	Scaled Tool Learning, Visual Search	GitHub
DeepSketcher: Internalizing Visual Manipulation for Multimodal Reasoning	Arxiv 2025	Visual Manipulation, Sketching, Internalized	GitHub
VLM-R3: Region Recognition, Reasoning, and Refinement for Enhanced Multimodal Chain-of-Thought	Arxiv 2025	Region Refinement, Recursive Focusing	N/A
VR-Thinker: Boosting Video Reward Models through Thinking-with-Image Reasoning	Arxiv 2025	Video Reward Models, Thinking-with-Image	GitHub
Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models	Arxiv 2024	Sketching, Visual Chain of Thought	GitHub
2026
Let's Think with Images Efficiently! An Interleaved-Modal Chain-of-Thought Reasoning Framework with Dynamic and Precise Visual Thoughts	AAAI 2026	Interleaved-Modal CoT, Dynamic Visual Thoughts	GitHub
Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm	CVPR 2026	Video Generation, Multimodal Reasoning Paradigm	GitHub
AGILE: Agentic Jigsaw Interaction Learning for Enhancing Visual Perception and Reasoning in VLMs	ICLR 2026	Agentic Interaction, Jigsaw Puzzle, Visual Perception	GitHub
DeepEyes: Incentivizing "Thinking with Images" in Vision-Language Models via Reinforcement Learning	ICLR 2026	Reinforcement Learning, Zoom/Crop Tools, Long CoT	GitHub
Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search	ICLR 2026	Visual Probing, Agentic Tools	GitHub
Thyme: Think Beyond Images	ICLR 2026	Pixel-space Operations, Code Generation	GitHub
Visual Planning: Let's Think Only with Images	ICLR 2026 Oral	Visual Planning, Image-only Reasoning	GitHub
2025
Argus: Vision-Centric Reasoning with Grounded Chain-of-Thought	CVPR 2025	Visual CoT, Attention Grounding	Project
ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding	ICML 2025	Visual Editing, Structured Understanding	GitHub
PixelReasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learning	NeurIPS 2025	Pixel-level Operations, Dynamic Visual Manipulation	GitHub
2024
Chain-of-Spot: Interactive Reasoning Improves Large Vision-Language Models	CVPR 2024	Interactive Spot Identification, Zoom-in Reasoning	GitHub
V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs	CVPR 2024	Visual Search, Search-based Perception	GitHub

⬆ Back to Top

---

Training-Based Methods

This category covers methods that improve fine-grained perception through training procedures, including supervised fine-tuning, knowledge distillation, and reinforcement learning.

Supervised Fine-Tuning & Distillation

Title	Venue & Year	Highlights/Keywords	Code
Preprints
Attention-guided Fine-tuning of Multimodal Large Language Models Improves Chain-of-Thought Reasoning	Arxiv 2026	Attention-Guided CoT-SFT, Delayed Answer Commitment, Visual-Token Access	N/A
Beyond Visual Memory: Mechanistic Diagnostics of Latent Visual Reasoning	Arxiv 2026	Latent Token Decomposition, Boundary Markers, Mechanistic Analysis	N/A
LanteRn: Latent Visual Structured Reasoning	Arxiv 2026	Latent Visual Reasoning, Structured Reasoning	N/A
Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step	Arxiv 2025	Image Generation CoT, Verification	GitHub
RedStar: Does Scaling Long-CoT Data Unlock Better Slow-Reasoning Systems?	Arxiv 2025	Long-CoT, Scaling	N/A
URSA: Understanding and Verifying Chain-of-thought Reasoning in Multimodal Mathematics	Arxiv 2025	Mathematical Reasoning, Verification	GitHub
AtomThink: A Slow Thinking Framework for Multimodal Mathematical Reasoning	Arxiv 2024	Slow Thinking, Mathematical Reasoning	GitHub
TextHawk: Exploring Efficient Fine-Grained Perception of Multimodal Large Language Models	Arxiv 2024	Efficient Fine-Grained Perception, Text-rich	GitHub
2026
Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodology	ICLR 2026	Traceable Evidence, Visual Grounded Reasoning	GitHub
Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception	ICML 2026	Region-to-Image Distillation, ZoomBench, Single-Pass Perception	GitHub
2025
Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models	CVPR 2025	Long-Chain Reasoning, Insightful Analysis	GitHub
Perception Tokens Enhance Visual Reasoning in Multimodal Language Models	CVPR 2025	Perception Tokens, Visual Reasoning	Project
SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoning	NeurIPS 2025	Depth Perception, Spatial Reasoning, Structured Rationales	GitHub
2024
Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition	ICML 2024	Video Reasoning, Perception to Cognition	GitHub

⬆ Back to Top

---

Reinforcement Learning

Title	Venue & Year	Highlights/Keywords	Code
2026
iVGR: Internalizing Visually Grounded Reasoning for MLLMs with Reinforcement Learning	ICML 2026	Visually Grounded Reasoning, Internalization, RL	N/A
PAPO: Perception-Aware Policy Optimization for Multimodal Reasoning	ICLR 2026	PAPO, Perception-Aware RL, Implicit Perception Supervision	GitHub
Perception-R1: Advancing Multimodal Reasoning Capabilities of MLLMs via Visual Perception Reward	ICLR 2026	Visual Perception Reward, RLVR, GRPO	GitHub
RAPID: Reasoning-Aligned Perception Decoupling for Scalable Multi-modal Reasoning	ICLR 2026	Perception-Decoupling, Reasoning Alignment, Two-stage Pipeline	GitHub
Spotlight on Token Perception for Multimodal Reinforcement Learning	ICLR 2026	Token Perception, Visual Dependency, RLVR Optimization	GitHub
ViPER: Empowering the Self-Evolution of Visual Perception Abilities in Vision-Language Models	ICLR 2026	Self-Evolution, Fine-Grained Perception, RL	GitHub
VisionReasoner: Unified Reasoning-Integrated Visual Perception via Reinforcement Learning	ICLR 2026	Unified Perception-Reasoning, RL, Multi-task	GitHub
VTool-R1: VLMs Learn to Think with Images via Reinforcement Learning on Multimodal Tool Use	ICLR 2026	Reinforcement Learning, Tool Use, Thinking-with-Images	GitHub
Preprints
Boosting Multimodal Reasoning with MCTS-Automated Structured Thinking	Arxiv 2025	MCTS, Structured Thinking	GitHub
Boosting the Generalization and Reasoning of VLMs with Curriculum Reinforcement Learning	Arxiv 2025	Curriculum RL, Generalization	N/A
LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL	Arxiv 2025	Two-Stage RL, Rule-based	GitHub
MedVLM-R1: Incentivizing Medical Reasoning Capability of VLMs via Reinforcement Learning	Arxiv 2025	Medical Reasoning, RL	GitHub
MM-Eureka: Exploring Visual Aha Moment with Rule-based Large-scale Reinforcement Learning	Arxiv 2025	Visual Aha Moment, Rule-based RL	GitHub
OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement	Arxiv 2025	Self-Improvement, Iterative Training	GitHub
R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcement Learning	Arxiv 2025	Emotion Recognition, Explainable RL	GitHub
R1-OneVision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization	Arxiv 2025	Cross-Modal, Generalized Reasoning	GitHub
Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement	Arxiv 2025	Segmentation, Cognitive Reinforcement	GitHub
Training Multi-Image Vision Agents via End2End Reinforcement Learning	Arxiv 2025	Multi-Image, End2End RL, Vision Agents	N/A
Virgo: A Preliminary Exploration on Reproducing o1-like MLLM	Arxiv 2025	O1-like MLLM, Reasoning Exploration	GitHub
VisualPRM: An Effective Process Reward Model for Multimodal Reasoning	Arxiv 2025	Process Reward Model	Project
VisualThinker-R1-Zero: R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model	Arxiv 2025	R1-Zero, Visual Reasoning	GitHub
VisRL: Intention-Driven Visual Perception via Reinforced Reasoning	Arxiv 2025	Intention-Driven, Reinforced Reasoning	GitHub
2025
LlamaV-o1: Rethinking Step-by-Step Visual Reasoning in LLMs	ACL-Findings 2025	Visual Reasoning, O1-style	GitHub
R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization	ICCV 2025	GRPO, Step-wise Reasoning	GitHub
Diving into Self-Evolving Training for Multimodal Reasoning	ICML 2025	Self-Evolving, RL Training	GitHub
Mulberry: Empowering MLLM with O1-like Reasoning and Reflection via Collective Monte Carlo Tree Search	NeurIPS 2025 Spotlight	MCTS, O1-like Reasoning	GitHub
ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs	NeurIPS 2025	Visual Hallucination Critic, RL Proxy Task, Fine-Grained Perception	GitHub

⬆ Back to Top

---

Applications & Domains

This category covers application domains where fine-grained perception is critical.

Title	Venue & Year	Domain	Highlights/Keywords	Code
Preprints
EmoOmni: Bridging Emotional Understanding and Expression in Omni-Modal LLMs	Arxiv 2026	Emotion	Omni-Modal, Emotional Understanding	N/A
Q-DeepSight: Incentivizing Thinking with Images for Image Quality Assessment and Refinement	Arxiv 2026	Image Quality	Thinking-with-Images for IQA, Refinement	N/A
Q-Probe: Scaling Image Quality Assessment to High Resolution via Context-Aware Agentic Probing	Arxiv 2026	Image Quality	Agentic Probing, High-Resolution IQA	N/A
VLA-Thinker: Boosting Vision-Language-Action Models through Thinking-with-Image Reasoning	Arxiv 2026	Robotics	VLA, Thinking-with-Image, Action Models	N/A
CoT-Drive: Efficient Motion Forecasting for Autonomous Driving with LLMs and Chain-of-Thought Prompting	Arxiv 2025	Autonomous Driving	Motion Forecasting, CoT	N/A
MedVLM-R1: Incentivizing Medical Reasoning Capability of VLMs via Reinforcement Learning	Arxiv 2025	Medical	Medical Reasoning, RL	GitHub
DriveCoT: Integrating Chain-of-Thought Reasoning with End-to-End Driving	Arxiv 2024	Autonomous Driving	End-to-End Driving, CoT	Github
Robotic Control via Embodied Chain-of-Thought Reasoning	Arxiv 2024	Robotics	Embodied CoT, Control	GitHub
2026
Grounding-IQA: Grounding Multimodal Language Model for Image Quality Assessment	ICLR 2026	Image Quality	Grounding-IQA, Multimodal Referring, Quality Assessment	GitHub
2024
ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulation	CVPR 2024	Robotics	Object-centric, Manipulation	GitHub
Dolphins: Multimodal Language Model for Driving	ECCV 2024	Autonomous Driving	Driving-specific, Multimodal	GitHub
Reason2Drive: Towards Interpretable and Chain-based Reasoning for Autonomous Driving	ECCV 2024	Autonomous Driving	Interpretable, Chain Reasoning	GitHub
MedCoT: Medical Chain of Thought via Hierarchical Expert	EMNLP 2024	Medical	Hierarchical Expert, Medical CoT	GitHub

⬆ Back to Top

---

Why We Do It

In an era where synthetic media is increasingly sophisticated and pervasive, our research serves as a critical line of defense. By advancing fine-grained perception technologies, we aim to:

• Enhance Visual Understanding: Enable MLLMs to perceive fine-grained details without expensive inference-time operations.
• Bridge the Zooming Gap: Internalize the benefits of "zooming in" during training for efficient single-pass perception.
• Industrial Application & Impact: We provide robust, scalable perception solutions for Ant Group's diverse content platforms.

✉️ Contact Us

For questions or collaborations, please contact:

• Liangbo He: liangbo.hlb@antgroup.com
• Lai Wei: waltonfuture@sjtu.edu.cn
• Jun Lan: yelan.lj@antgroup.com
• Zhuosheng Zhang: zhangzs@sjtu.edu.cn
• Xianjie Liu: liuxianjie.scu@vip.163.com

⬆ Back to Top

---

Star History