Skip to content
conftrace_

Wei Zhan

35 papers · 2020–2026 · 9 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓
+7 more ↓ πŸ—ΊοΈ Taxonomy Completionist (54) πŸƒ Academic Marathon Β· Sprint 🌍 Conference Polyglot Β· Silver πŸŒ‰ Interdisciplinary Bridge Β· Silver 🐣 Hot Topic Early Bird
🀝 Dynamic Duo (32) πŸ† Keyword Champion (2) 🌈 Renaissance Researcher (5) πŸ”₯ Unstoppable Β· Bronze ⚑ Prolific Year Β· Productive πŸ’Ž Century Club Β· Bronze πŸ—ƒοΈ Keyword Collector (139)

Venues

CVPR (8) ECCV (7) CoRL (5) ICCV (4) ICLR (4) NeurIPS (4) AISTATS (1) ICML (1) RSS (1)

Top co-authors

Masayoshi Tomizuka (32) Chenfeng Xu (16) Mingyu Ding (10) Yichen Xie (8) Chen Tang (8) Kurt Keutzer (8) Chensheng Peng (8) Yixiao Wang (4) Chenran Li (4) Bichen Wu (3)

Research topics

Deep Learning (16) Computer Vision (15) Machine Learning (13) Artificial Intelligence (10) Analysis (10) Domain-Specific (9) Core AI (8) Models (7) Architectures (6) Core Methods (5) Learning Types Β· Deep Learning (5) Learning Types Β· Machine Learning (5) Reinforcement Learning (4) Robotics (3) Capabilities (3)

Keywords

autonomous driving (6) trajectory prediction (3) 3d object detection (3) foundation model (3) reinforcement learning (2) annotation budget (2) multi-sensor fusion (2) imitation learning (2) depth estimation (2) cross-modal learning (2) motion estimation (2) diffusion model (2) 3d gaussian splatting (2) autonomous vehicle (2) object detection (2) sparse representation (2) active learning (2) offline reinforcement learning (2) point cloud (2) policy customization (2)

Papers

Learning to Drive is a Free Gift: Large-Scale Label-Free Autonomy Pretraining from Unposed In-The-Wild Videos CVPR 2026 NoRD: A Data-Efficient Vision-Language-Action Model that Drives without Reasoning CVPR 2026 RAYNOVA: Scale-Temporal Autoregressive World Modeling in Ray Space CVPR 2026 CompGS: Unleashing 2D Compositionality for Compositional Text-to-3D via Dynamically Optimizing 3D Gaussians CVPR 2025 DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes CVPR 2025 DexHandDiff: Interaction-aware Diffusion Planning for Adaptive Dexterous Manipulation CVPR 2025 LANGTRAJ: Diffusion Model and Dataset for Language-Conditioned Trajectory Simulation ICCV 2025 MEReQ: Max-Ent Residual-Q Inverse RL for Sample-Efficient Alignment from Intervention CoRL 2025 Residual-MPPI: Online Policy Customization for Continuous Control ICLR 2025 WOMD-Reasoning: A Large-Scale Dataset for Interaction Reasoning in Driving ICML 2025 X-Drive: Cross-modality Consistent Multi-Sensor Data Synthesis for Driving Scenarios ICLR 2025 Human-oriented Representation Learning for Robotic Manipulation RSS 2024 Optimizing Diffusion Models for Joint Trajectory Prediction and Controllable Generation ECCV 2024 Q-SLAM: Quadric Representations for Monocular SLAM CoRL 2024 Safe-Sim: Safety-Critical Closed-Loop Traffic Simulation with Diffusion-Controllable Adversaries ECCV 2024 Sparse Diffusion Policy: A Sparse, Reusable, and Flexible Policy for Robot Learning CoRL 2024 Towards Generalizable and Interpretable Motion Prediction: A Deep Variational Bayes Approach AISTATS 2024 UniAdapter: Unified Parameter-Efficient Transfer Learning for Cross-modal Modeling ICLR 2024 Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning Paradigm CVPR 2023 DELFlow: Dense Efficient Learning of Scene Flow for Large-Scale Point Clouds ICCV 2023 Doubly-Robust Self-Training NeurIPS 2023 NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection ICCV 2023 Residual Q-Learning: Offline and Online Policy Customization without Value NeurIPS 2023 SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection ICCV 2023 Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detection ICLR 2023 Towards Free Data Selection with General-Purpose Models NeurIPS 2023 DetMatch: Two Teachers Are Better than One for Joint 2D and 3D Semi-Supervised Object Detection ECCV 2022 Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Models ECCV 2022 PreTraM: Self-Supervised Pre-training via Connecting Trajectory and Map ECCV 2022 What Matters for 3D Scene Flow Network ECCV 2022 Dealing with the Unknown: Pessimistic Offline Reinforcement Learning CoRL 2021 Exploring Social Posterior Collapse in Variational Autoencoder for Interaction Modeling NeurIPS 2021 Multi-Agent Trajectory Prediction by Combining Egocentric and Allocentric Views CoRL 2021 Sparse R-CNN: End-to-End Object Detection With Learnable Proposals CVPR 2021 SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation ECCV 2020