[CVPR 2026 (Oral)] MAGICIAN: Efficient Long-Term Planning with Imagined Gaussians for Active Mapping

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Open Lakehouse Format for Multimodal AI. Convert from Parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, a…

Codebase for DexMachina: Functional Retargeting for Bimanual Dexterous Manipulation

An agentic skills framework & software development methodology that works.

Claude Code skill implementing Manus-style persistent markdown planning — the workflow pattern behind the $2B acquisition.

Masked Depth Modeling for Spatial Perception

Official repository of paper "CoMoVi: Co-Generation of 3D Human Motions and Realistic Videos"

A comprehensive list of papers for the definition of World Models and using World Models for General Video Generation, Embodied AI, and Autonomous Driving, including papers, codes, and related webs…

HY-Motion model for 3D human motion or 3D character animation generation.

[CVPR 2026] G2VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning

[CVPR 2026] Dexterous World Models

[CVPR 2026 Highlight] LitePT: Lighter Yet Stronger Point Transformer

Code for "EgoX: Egocentric Video Generation from a Single Exocentric Video"

🔥🔥🔥 [IEEE TCSVT] Latest Papers, Codes and Datasets on Vid-LLMs.

Native and Compact Structured Latents for 3D Generation

🏂 Training-Free Human Mesh Recovery from Videos, based on SAM-3, Diffusion-VAS, and SAM-3D-Body.

Fully Open Framework for Democratized Multimodal Reinforcement Learning.

Fully Open Framework for Democratized Multimodal Reinforcement Learning.

Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.

A Curated List of Awesome Works in World Modeling, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts Interested in World Modeling.

TextOp: Real-time Interactive Text-Driven Humanoid Robot Motion Generation and Control

SAM 3D Objects

A Curated List of Awesome Works in World Modeling, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts Interested in World Modeling.

An open-source, GPU-accelerated physics simulation engine built upon NVIDIA Warp, specifically targeting roboticists and simulation researchers.

The Lightning Grasp System

Isaac Lab API, powered by MuJoCo-Warp, for RL and robotics research

Official Code for CVPR2025 Paper: LatentHOI: On the Generalizable Hand Object Motion Generation with Latent Hand Diffusion

[ICCV'25] Method for generating static human-object interactions