Official implementation of NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous Environments (ICCV'25).

Official implementation of paper "Unified World Models: Memory-Augmented Planning and Foresight for Visual Navigation"

A list of works on video generation towards world model

A Collection of Diffusion for Path Planning Papers, Toolboxes and Notes.

WorldPlay: Interactive World Modeling with Real-Time Latency and Geometric Consistency

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…

[TRO 2025] NeuPAN: Direct Point Robot Navigation with End-to-End Model-based Learning.

[CVPR 2025 Highlight] MATCHA: Towards Matching Anything

Official repository for "RLVR-World: Training World Models with Reinforcement Learning" (NeurIPS 2025), https://arxiv.org/abs/2505.13934

Vision-Language Navigation Benchmark in Isaac Lab

OmniVGGT: Omni-Modality Driven Visual Geometry Grounded Transformer

Collect some World Models for Autonomous Driving (and Robotic, etc.) papers.

[IROS 2025 oral] Official implementation of NOLO: Navigate Only Look Once

A most Frontend Collection and survey of vision-language model papers, and models GitHub repository. Continuous updates.

[AAAI 2024] Mono3DVG: 3D Visual Grounding in Monocular Images, AAAI, 2024

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

The version 2 of Mono 3D visiual grounding

Official code release for CoRL'25 paper: VT-Refine: Learning Bimanual Assembly with Visuo-Tactile Feedback via Simulation Fine-Tuning

Repository of the paper "AnyUp: Universal Feature Upsampling".

Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"

Reading list for research topics in embodied vision

This is the code for the IROS2025 RoboSense challenge track1: LLM for Driving

Robot Learning Beyond Earth

[ACMMM 2025] Official implementation of SeqVLM: Proposal-Guided Multi-View Sequences Reasoning via VLM for Zero Shot 3D Visual Grounding

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

SLAM-Former: Putting SLAM into One Transformer

[CVPR'25] SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding