From Foundation to Application

iMac: Translating Actions into Motion and Contact Images for Embodied World Models

[Arxiv 2026] Toward the Whole Picture: Accumulative Fingerprint Mapping and Reconstruction for Small-Area Mobile Sensors

The official application of Identity-Consistent Multi-Pose Generation of Contactless Fingerprints

GesVLA: Gesture-Aware Vision-Language-Action Model with Embedded Representations

[CVPR 2026] AwareVLN: Reasoning with Self-awareness for Vision-Language Navigation

[ACL 2026 Poster] Code and Benchmark for "Do MLLMs Understand Pointing? Benchmarking and Enhancing Referential Reasoning in Egocentric Vision"

RoboChallenge Inference example code

The official code of Yume

Official Hardware Codebase for the Paper "BEHAVIOR Robot Suite: Streamlining Real-World Whole-Body Manipulation for Everyday Household Activities"

[ICCV 2025] D^3QE: Learning Discrete Distribution Discrepancy-aware Quantization Error for Autoregressive-Generated Image Detection

[ICLR 2026] Code of "MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation"

Codes, datasets, and synthetic dataset generator about the paper "LiCamPose: Combining Multi-View LiDAR and RGB Cameras for Robust Single-Snapshot 3D Human Pose Estimation"

Nav-R1: Reasoning and Navigation in Embodied Scenes

[CoRL 2025] GC-VLN: Instruction as Graph Constraints for Training-free Vision-and-Language Navigation

[ICRA 2026] Official implementation of the paper: "StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling"

[ICCV 2025] IGL-Nav: Incremental 3D Gaussian Localization for Image-goal Navigation

RoboBrain 2.5: Advanced version of RoboBrain. Depth in Sight, Time in Mind. 🎉🎉🎉

VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and cloud.

[CoRL 2025] Repository relating to "TrackVLA: Embodied Visual Tracking in the Wild"

Official implementation of "OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoning"

[CoRL25] GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data

GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models

[ICML 2025 Oral] Official repo of EmbodiedBench, a comprehensive benchmark designed to evaluate MLLMs as embodied agents.

[WACV'24] TD3D: Top-Down Beats Bottom-Up in 3D Instance Segmentation

[RSS'25] This repository is the implementation of "NaVILA: Legged Robot Vision-Language-Action Model for Navigation"

Code for OctoNav-Bench and OctoNav-R1

This is a PyTorch implementation of MCLN proposed by our paper "Multi-branch Collaborative Learning Network for 3D Visual Grounding"(ECCV2024)