1

MAD: Memory-Augmented Detection of 3D Objects

_CVPR 2025_ Pushing the boundaries of Memory-based Perception

DIO: Decomposable Implicit 4D Occupancy-Flow World Model

_CVPR 2025_ Object-Centric Occupancy Foundation Model

DeTra: A Unified Model for Object Detection and Trajectory Forecasting

_ECCV 2024_ Unified object detection and trajectory prediction as trajectory refinement.

UnO: Unsupervised Occupancy Fields for Perception and Forecasting

_CVPR 2024_ __(Oral)__ Occupancy Foundation Model (Unsupervised)

QuAD: Query-based Interpretable Neural Motion Planning for Autonomous Driving

_ICRA 2024_ End-to-end autonomy leveraging implicit occupancy.

Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion

_ICLR 2024_ LiDAR World Model.

ImplicitO: Implicit Occupancy Flow Fields for Perception and Prediction in Self-Driving

_CVPR 2023_ __(Highlight)__ Efficient implicit occupancy perception and forecasting model.

TrafficSim: Learning to Simulate Realistic Multi-Agent Behaviors

_CVPR 2021_ Realistic long-term vehicle behavior simulation learned from imitation and common sense

Strobe: Streaming Object Detection from LiDAR Packets

_CoRL 2020_ __(Spotlight)__ Existing LiDAR perception systems wait 100ms just to build a sweep. StrObe instead does streaming detection from LiDAR packets and achieve an end-to-end latency of 21ms

Implicit Latent Variable Model for Scene-Consistent Motion Forecasting

_ECCV 2020_ ILVM characterizes the joint distribution over multiple actors' future trajectories