Stars
a 2D rigid body physics engine for the web ▲● ■
Graphium: Scaling molecular GNNs to infinity.
MiniMol is a 10M-parameters molecular fingerprinting model pre-trained on >3300 biological and quantum tasks
Accurate ADMET Prediction with XGBoost
A Deep Learning Toolkit for DTI, Drug Property, PPI, DDI, Protein Function Prediction (Bioinformatics)
Therapeutics Commons (TDC): Multimodal Foundation for Therapeutic Science
Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team.
Official Code for "Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search"
[NeurIPS 2024 D&B] GTA: A Benchmark for General Tool Agents
An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models
[ICLR'26] Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodology
🟣 LLMs interview questions and answers to help you prepare for your next machine learning and data science interview in 2026.
Official repo for "PAPO: Perception-Aware Policy Optimization for Multimodal Reasoning"
[ICLR'25] Reconstructive Visual Instruction Tuning
✨✨ [ICLR 2026] R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning
The official code of "VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning" [NeurIPS25]
Training VLM agents with multi-turn reinforcement learning
arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv
Extend OpenRLHF to support LMM RL training for reproduction of DeepSeek-R1 on multimodal tasks.
[ICLR 2025] VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation
VARGPT-v1.1: Improve Visual Autoregressive Large Unified Model via Iterative Instruction Tuning and Reinforcement Learning
[CVPR2025] Official Implementation of ILLUME+
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL