Pinned Loading

1. AI-Can-Learn-Scientific-Taste AI-Can-Learn-Scientific-Taste Public

   We propose Reinforcement Learning from Community Feedback (RLCF), a training paradigm that uses large-scale community signals as supervision, and formulate scientific taste learning as a preference…

   432 11

2. Thinking-with-Video Thinking-with-Video Public

   We introduce 'Thinking with Video', a new paradigm leveraging video generation for multimodal reasoning. Our VideoThinkBench shows that Sora-2 surpasses GPT5 by 10% on eyeballing puzzles and reache…

   Python 320 6

3. Game-RL Game-RL Public

   Game-RL: Synthesizing Multimodal Verifiable Game Data to Boost VLMs' General Reasoning

   Python 160 3

4. pjlab-sys4nlp/llama-moe pjlab-sys4nlp/llama-moe Public

   ⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training (EMNLP 2024)

   Python 1k 61

5. MathTrap MathTrap Public

   In this work, we investigate the compositionality of large language models (LLMs) in mathematical reasoning. Specifically, we construct a new dataset MATHTRAP‡ by introducing carefully designed log…

   Python 59 1

6. Awesome-Agent-RL Awesome-Agent-RL Public

   A curated list of awesome resources about reward construction for AI agents. This repository covers cutting-edge research, and practical guides on defining and collecting rewards to build more inte…

   61 2