[ICML 2026] Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization

FoldFlow: SE(3)-Stochastic Flow Matching for Protein Backbone Generation

[ECCV 2024] Omni6DPose: A Benchmark and Model for Universal 6D Object Pose Estimation and Tracking

[SIGGRAPH 2026 Conference] FreeOrbit4D: Training-free Arbitrary Camera Redirection for Monocular Videos via Foreground-Complete 4D Reconstruction

Official DeiT repository

An offline-first scientific writing workspace powered by Claude. LaTeX + Python + 100+ scientific skills all running locally.

Community plugin to control Blender 3D with any LLM of your choice

HunyuanVideo-1.5: A leading lightweight video generation model

从零开始玩转OpenClaw：最全面的中文教程，涵盖安装、配置、实战案例和避坑指南（github版）

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Productive, portable, and performant GPU programming in Python.

Infinite Photorealistic Worlds using Procedural Generation

YaRN: Efficient Context Window Extension of Large Language Models

Advancing Open-source World Models

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…

Official code of ``2D Gaussians Spatial Transport for Point-supervised Density Regression'' (GST), AAAI 26.

Official repo for paper "MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions"

[NeurIPS 2025] Sekai: A Video Dataset towards World Exploration

A unified inference and post-training framework for accelerated video generation.

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…

🔥 Latest advances in Video Object Segmentation (VOS) – papers, datasets, and projects.

Cameras as Relative Positional Encoding

HY-World 1.5: A Systematic Framework for Interactive World Modeling with Real-Time Latency and Geometric Consistency

[ICCV 2023] Consistent Image Synthesis and Editing

This repository includes the official implementation of our paper "Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers"

Code release for paper "Test-Time Training Done Right"

SimWorld: An Open-ended Realistic Simulator for Autonomous Agents in Physical and Social Worlds