Towards Long-Horizon Vision-Language Navigation: Platform, Benchmark and Method (CVPR-25)

Implementation of VLM4VLA

Official implementation of paper Neural Green’s Functions (NeurIPS 2025)

Implementation for VPBench proposed in paper Visually Prompted Benchmarks Are Surprisingly Fragile

[RA-L 2025] FrontierNet: Learning Visual Cues to Explore

The official repository of BEAR: Benchmarking and Enhancing Multimodal Language Models with Atomic Embodied Capabilities

Public release for "Explore until Confident: Efficient Exploration for Embodied Question Answering"

Vision-and-Language Navigation in Continuous Environments using Habitat

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

A simulation platform for versatile Embodied AI research and developments.

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

Thinking in 360°: Humanoid Visual Search in the Wild

Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success

Training Visual Reasoners with Multimodal Verifiers

The Best Agent Harness. Meet Sisyphus: The Batteries-Included Agent that codes like you.

[NeurIPS 2025] EOC-Bench, an innovative benchmark designed to systematically evaluate object-centric embodied cognition in dynamic egocentric scenarios.

[ECCV 2024 Oral 🔥] Arc2Face: A Foundation Model for ID-Consistent Human Faces ------------------------ [ICCVW 2025] ID-Consistent, Precise Expression Generation with Blendshape-Guided Diffusion

Toward Ambulatory Vision: Learning Visually-Grounded Active View Selection

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

Official implementation of "Repurposing Video Diffusion Transformers for Robust Point Tracking"

Dexterous World Models

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

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

Unofficial reimplementation of VLA-0 using TRL's SFTTrainer.

Native and Compact Structured Latents for 3D Generation