Autonomous Vehicles

Vista: a novel driving world model achieving high-fidelity prediction and versatile controllability, outperforming state-of-the-art models in generalization and prediction accuracy.

VeXKD: A versatile framework boosts 3D perception by cleverly combining cross-modal fusion and knowledge distillation, improving single-modal student model accuracy without extra inference time.

MapUnveiler: a novel paradigm for online vectorized HD map construction that leverages clip-level token interaction and propagation to unveil hidden map elements and achieve state-of-the-art performan…

TopoLogic uses lane geometry and query similarity to improve lane topology reasoning in autonomous driving, significantly outperforming existing methods.

SMART: a scalable, real-time multi-agent driving simulator using next-token prediction, achieves state-of-the-art results and zero-shot generalization.

SimGen: Simulator-conditioned driving scene generation, uses a novel cascade diffusion pipeline to generate diverse driving scenes by mixing real-world and simulator data, addressing Sim2Real gaps.

SceneDiffuser: a scene-level diffusion model revolutionizes driving simulation by uniting scene initialization and rollout, enabling efficient and controllable closed-loop traffic generation.

BeTopNet uses braid theory to create a topological representation of multi-agent future driving behaviors, improving prediction and planning accuracy in autonomous driving systems.

RCDN: Robust, camera-insensitive collaborative perception via dynamic 3D neural modeling, overcoming camera failures for high-performance autonomous systems.

RadarOcc: Revolutionizing autonomous driving with robust 3D occupancy prediction using 4D imaging radar, overcoming limitations of LiDAR and camera-based approaches.

New large-scale dataset and model boost on-road object importance estimation accuracy by 23.1%!

RealMotion: a novel motion forecasting framework for continuous driving that outperforms existing methods by accumulating historical scene information and sequentially refining predictions, achieving …

LiDAR Translator (LiT) unifies diverse LiDAR data through a novel data-driven translation framework, enabling zero-shot and multi-domain joint learning, thus improving autonomous driving systems.

V2X-Graph: a novel cooperative motion forecasting framework achieving interpretable trajectory feature fusion for enhanced accuracy.

InteractTraj: Generating realistic, interactive traffic trajectories from natural language!

LaKD: a novel length-agnostic knowledge distillation framework enables accurate trajectory prediction regardless of observation length, overcoming limitations of existing methods.

Place3D optimizes LiDAR placement for superior 3D scene understanding.

Fourier Neural Processes (FNP) revolutionizes data assimilation by enabling accurate analysis of observations with varying resolutions, improving weather forecasting and Earth system modeling.

DeMo: Decoupling motion forecasting into directional intentions and dynamic states for improved autonomous driving.

CRT-Fusion: Boosting 3D object detection by fusing camera, radar, and motion information for more accurate, robust results!