Pytorch Implementation of Reliable Thinking with Images.

[ACL'26 Main] Beyond Majority Voting: Towards Fine-grained and More Reliable Reward Signal for Test-Time Reinforcement

Collection of latest papers and materials in the area of RLVR!

[ACL'26] Official Repository for The Paper: What If Consensus Lies? Selective-Complementary Reinforcement Learning at Test Time

[CVPR2026] Chain of World: World Model Thinking in Latent Motion

Official code of Motus: A Unified Latent Action World Model

Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

Official codebase for Fast-WAM: Do World Action Models Need Test-time Future Imagination?

[RSS 2023] Diffusion Policy Visuomotor Policy Learning via Action Diffusion

UniRL is a Framework for Unified Multimodal Model Reinforcement Learning

[ICML 2026] ZwZ model family: SOTA fine-grained perception performace; ZoomBench: a new challenging perception benchmark

NVIDIA Isaac GR00T N1.7 - A Foundation Model for Generalist Robots.

Code to pretrain, fine-tune, and evaluate DreamZero and run sim & real-world evals

Can VLA Models Learn from Real-World Data Continually without Forgetting?

Wan: Open and Advanced Large-Scale Video Generative Models

[ICLR'26 Oral] Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Prompts

[ICML 2026] LaST​$_0$​: Latent Spatio-Temporal Chain-of-Thought for Robotic Vision-Language-Action Model

Implementation of Unified-Action-Model

VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model

[ICLR 2026] SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

A curated collection of papers and resources on On-Policy Distillation for Large Language Models.

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

MCITlib: Multimodal Continual Instruction Tuning Library and Benchmark

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

Official Repository of Absolute Zero Reasoner

A Survey of Reinforcement Learning for Large Reasoning Models

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io