[ICLR 2026] ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving

Official implementation of "WILD-Drive: Off-Road Scene Captioning and Path Planning via Robust Multi-modal Routing and Efficient Large Language Model

[CVPR 2026] U4D: Uncertainty-Aware 4D World Modeling from LiDAR Sequences

[CVPR 2026] WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World

🌐 Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systems

[ICLR 2026] RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning

[CVPR 2026] ReasonMap: Towards Fine-Grained Visual Reasoning from Transit Maps

[ICRA 2025] WeatherGS: 3D Scene Reconstruction in Adverse Weather Conditions via Gaussian Splatting

[AAAI 2026] Generating Weather in any 3D Gaussian Scene

[CVPR 2025 Oral & Best Paper Finalist] Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models

ICRA 2026: ORAD-3D, a large-scale off-road autonomous driving dataset. Tasks: 2D free-space detection, 3D occupancy prediction, rough GPS-guided path planning, vision-language model-driven autonomo…

[CVPR 2025] UniScene: Unified Occupancy-centric Driving Scene Generation

[IEEE-IV 2025] V2X-Gaussians: Gaussian Splatting for Multi-Agent Cooperative Dynamic Scene Reconstruction

[ICCV2025] BézierGS: Dynamic Urban Scene Reconstruction with Bézier Curve Gaussian Splatting

CaFNet: A Confidence-Driven Framework for Radar Camera Depth Estimation

[RA-L 25] Self-Supervised Diffusion-Based Scene Flow Estimation and Motion Segmentation with 4D Radar

The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…

[CVPR 2026 MAIN] OmniVGGT: Omni-Modality Driven Visual Geometry Grounded Transformer

Source code for [TRO2025] VINGS-Mono: Visual Inertial Gaussian Splatting Monocular SLAM in Large Scenes.

Official implement of VGGT-Long

[CVPR 2025] Official code for the paper "SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis"

[IJCV 2024] SplatFlow: Learning Multi-frame Optical Flow via Splatting

[CVPR 2022] RADIAl: Raw High-Definition Radar for Multi-Task Learning

4D Radar Object Detection for Autonomous Driving in Various Weather Conditions

This repository shares the documentation and development kit of the View of Delft automotive dataset.

(T-IV) Radar4Motion: 4D Imaging Radar based IMU-free Odometry with Radar Cross Section (RCS) weighted Correspondences

GBlobs: Explicit Local Structure via Gaussian Blobs for Improved Cross-Domain LiDAR-based 3D Object Detection

This repo lists relevant papers summarized in our survey paper: A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models.

[TMM 2026]. Boosting Instance Awareness via Cross-View Correlation with 4D Radar and Camera