[ICLR 2026] Codebase for paper "Geometry-aware 4D Video Generation for Robot Manipulation"

Official code of Motus: A Unified Latent Action World Model

Implementation of "EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer"(ICCV2025)

[ICLR 2026] Trace Anything: Representing Any Video in 4D via Trajectory Fields

[NeurIPS 2025 (Spotlight)] The implementation for the paper "4DGT Learning a 4D Gaussian Transformer Using Real-World Monocular Videos"

[CVPR25 Highlight] Instant Gaussian Stream: Fast and Generalizable Streaming of Dynamic Scene Reconstruction via Gaussian Splatting

Official repository of Learning to Act from Actionless Videos through Dense Correspondences.

[CVPR 2025] VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulation

(CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

[ICLR 2026] An official implementation of "SIM-CoT: Supervised Implicit Chain-of-Thought"

[NeurIPS 2025] DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge

Official repository for LTX-Video

[ICLR2026] SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training

MokA: Multimodal Low-Rank Adaptation for MLLMs

[AAAI26 oral] CronusVLA: Towards Efficient and Robust Manipulation via Multi-Frame Vision-Language-Action Modeling

[ICLR 2026 Oral] DiffusionNFT: Online Diffusion Reinforcement with Forward Process

[RA-L2025] ActiveGS: Active Scene Reconstruction Using Gaussian Splatting

Code for "Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation"

[CoRL 2025] Pretraining code for FLOWER VLA on OXE

Official code of paper "DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution"

[NeurIPS 2021] [T-PAMI] DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification

Official implementation of “4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Models” (CVPR 2025)

[NeurIPS 2025] LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPS

Repo for SeedVR2 (ICLR2026) & SeedVR (CVPR2025 Highlight)

Official implementation of "APEX: Action Priors Enable Efficient Exploration for Skill Imitation on Articulated Robots"

The simplest, fastest repository for training/finetuning medium-sized GPTs.

ORION: Option-Regularized Deep Reinforcement Learning for Cooperative Multi-Agent Online Navigation