Offical code release for DynoSAM: Dynamic Object Smoothing And Mapping. Accepted Transactions on Robotics (Visual SLAM SI). A visual SLAM framework and pipeline for Dynamic environements, estimatin…

[SIGGRAPH Asia 2023 (Technical Communications)] EasyVolcap: Accelerating Neural Volumetric Video Research

Code for the SIGGRAPH 2021 paper "Consistent Depth of Moving Objects in Video".

Sharp Monocular View Synthesis in Less Than a Second

"E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training" official implementation.

Galaxea's first VLA release

GitHub page for "Large Language Model-Brained GUI Agents: A Survey"

Paper Debugger is the best overleaf companion

Visual Imitation Enables Contextual Humanoid Control. CoRL 2025, Best Student Paper Award.

Turn GitHub repositories into LLM tools. (ACL 2025)

[ASPLOS 2026] CLM: Removing the GPU Memory Barrier for 3D Gaussian Splatting with CPU Offloading

Official implementation of "MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second".

Latent Collaboration in Multi-Agent Systems

Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation

[CVPR 2025 Highlight] GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control

The official implementation of the paper “VGGT4D: Mining Motion Cues in Visual Geometry Transformers for 4D Scene Reconstruction.”

🎤 Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching

Official implementation of "S²M²: Scalable Stereo Matching Model for Reliable Depth Estimation, ICCV 2025"

The official implementation for [NeurIPS2025 Oral] Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free

[TMLR 2024] repository for VLN with foundation models

Fara-7B: An Efficient Agentic Model for Computer Use

📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉

VLA-0: Building State-of-the-Art VLAs with Zero Modification

Depth Anything 3

Official implementation of "Understanding multi-view transformers" (ICCV 2025 E2E3D Workshop)

Official Implementation of Driv3R

AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibration (ICCV 2025)

[ICCV'25 Best Paper Finalist] ReCamMaster: Camera-Controlled Generative Rendering from A Single Video

[CVPR2025] CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos