Stars
Vision-OPD is a regional-to-global on-policy self-distillation framework that transfers a model's own privileged crop-conditioned perception to its full-image policy, enabling fine-grained visual u…
Imagine Before You Predict: Interleaved Latent Visual Reasoning for Video Event Prediction
On Policy Distillation Build on top of Verl
Official implementation of paper "VLM³: Vision Language Models Are Native 3D Learners".
State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!
Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe
PyTorch-based open-source code for paper "SOD: Step-wise On-policy Distillation for Small Language Model Agents"
[ICML 2026] ZwZ model family: SOTA fine-grained perception performace; ZoomBench: a new challenging perception benchmark
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
A curated, continuously updated reading list, paper blogs, and resources for World Action Models (WAMs) in embodied AI.
DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm
4DThinker: Thinking with 4D Imagery for Dynamic Spatial Understanding
Fully Open Framework for Democratized Multimodal Training
Official repository for the paper "Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation"
The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.
Offical Implementation for "Recursive Multi-Agent Systems"
JiuwenSwarm is an intelligent AI Agent built on openJiuwen. It extends the powerful capabilities of large language models directly to your fingertips through various communication apps you use daily.
OpenGame: Open Agentic Coding for Games
Code search MCP for Claude Code. Make entire codebase the context for any coding agent.
A Curated List of Vision-Language-Action (VLA) and World Action Models (WAM) Research and Beyond
VS-Bench: Evaluating VLMs for Strategic Reasoning and Decision-Making in Multi-Agent Environments