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

Post-training scripts and samples for NVIDIA Cosmos ecosystem

Vision-and-Language Navigation in Continuous Environments using Habitat

An official code release of BEVHeight++

[CVPR 2026] GaussianDWM: 3D Gaussian Driving World Model for Unified Scene Understanding and Multi-Modal Generation

"Paper2Slides: From Paper to Presentation in One Click"

A LaTeX template for journal review response (initially designed for IEEE TVCG)

Reference PyTorch implementation and models for DINOv3

[ECCV 2024] Scene as Gaussians for Vision-Based 3D Semantic Occupancy Prediction

[CVPR 2023 Best Paper Award] Planning-oriented Autonomous Driving

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

[AAAI 2026 Oral] LiDARCrafter: Dynamic 4D World Modeling from LiDAR Sequences

[ICCV 2023] Robo3D: Towards Robust and Reliable 3D Perception against Corruptions

[NeurIPS2021] Code Release of K-Net: Towards Unified Image Segmentation

PyTorch code and models for ScaLR image-to-lidar distillation method

IJCV 2026 Compact GS-SLAM

This work investigates automatic hyperparameter tuning for planners such as DWA and TEB, and our navigation framework LE-Nav can be used to adjust hyperparameters of any optimization-based planner.

[T-ASE 25] SegNet4D: Efficient Instance-Aware 4D Semantic Segmentation for LiDAR Point Cloud

SOTA LiDAR Global Descriptor in LiDAR Place Recognition (accepted in RA-L'24 w/ ICRA'25)

(ICRA 2025) This repository is the official code for PoLaRIS:A Pohang Canal Object Detection and Tracking Dataset in Maritime Environments

Code that runs on the Open Source Rover

State-of-the-art methods for human trajectory forecasting. Contains code for papers published at ECCV 2020 and ICCV 2021.

[CVPR 2025] MNE-SLAM

OpenPCSeg: Open Source Point Cloud Segmentation Toolbox and Benchmark

[CVPR 2024] PLGSLAM