Change the repository type filter
All
Repositories list
18 repositories
- We introduce Reasoning via Video, a new paradigm that uses maze-solving video generation to probe multimodal reasoning; our VR-Bench shows that fine-tuned video models consistently outperform strong VLMs on long-horizon spatial planning tasks.
- 🔥🔥🔥 ICLR 2025 Oral. Automating Agentic Workflow Generation.
.github
PublicStanfordTown
PublicMetaGPT-Ext
PublicMinecraft
PublicAoT
Public