Stars
Forecasting scientific progress with AI
🔍 OpenSearch-VL provides a fully open recipe for training strong multimodal deep search agents through high-quality data curation, diverse visual/search tools, and fatal-aware agentic reinforcement…
OpenGame: Open Agentic Coding for Games
Ultra-light Harness scaffolding for AI agents, a mini version of claude code
Gen-Searcher: Reinforcing Agentic Search for Image Generation
🔥 LeetCode for PyTorch — practice implementing softmax, attention, GPT-2 and more from scratch with instant auto-grading. Jupyter-based, self-hosted or try online.
[ICML 2026] Multimodal deep-research MLLM and benchmark. The first long-horizon multimodal deep-research MLLM, extending the number of reasoning turns to dozens and the number of search-engine inte…
Unlocking Iterative Reasoning for Any Image Editor
🔥 OneThinker: All-in-one Reasoning Model for Image and Video [CVPR 2026]
[NeurIPS'25] VLMs Can Aggregate Scattered Training Patches
Video-R1: Reinforcing Video Reasoning in MLLMs [🔥the first paper to explore R1 for video]
A python script for downloading huggingface datasets and models.
Litex: The Language Where Mathematics Verifies Itself.
✅（已完结）超级全面的 深度学习 笔记【土堆 Pytorch】【李沐 动手学深度学习】【吴恩达 深度学习】【大飞 大模型Agent】
Awesome-Fudan: a code repository list of computer courses at Fudan University