Bolei Zhou

AniMimic: Imitating 3D Animation from Video Priors CVPR 2026 AURA: Multi-modal Shared Autonomy for Urban Navigation CVPR 2026 Group Diffusion: Enhancing Image Generation by Unlocking Cross-Sample Collaboration CVPR 2026 Vista4D: Video Reshooting with 4D Point Clouds CVPR 2026 3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting ICLR 2025 Embodied Scene Understanding for Vision Language Models via MetaVQA CVPR 2025 Hyper: Hyperparameter Robust Efficient Exploration in Reinforcement Learning ICML 2025 Learning to Generate Diverse Pedestrian Movements from Web Videos with Noisy Labels ICLR 2025 MetaUrban: An Embodied AI Simulation Platform for Urban Micromobility ICLR 2025 Occupancy Learning with Spatiotemporal Memory ICCV 2025 Robot-Gated Interactive Imitation Learning with Adaptive Intervention Mechanism ICML 2025 Towards Autonomous Micromobility through Scalable Urban Simulation CVPR 2025 TurboTrain: Towards Efficient and Balanced Multi-Task Learning for Multi-Agent Perception and Prediction ICCV 2025 V2XPnP: Vehicle-to-Everything Spatio-Temporal Fusion for Multi-Agent Perception and Prediction ICCV 2025 Verbalized Representation Learning for Interpretable Few-Shot Generalization ICCV 2025 Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigation CVPR 2025 WOMD-Reasoning: A Large-Scale Dataset for Interaction Reasoning in Driving ICML 2025 X-Fusion: Introducing New Modality to Frozen Large Language Models ICCV 2025 BerfScene: Bev-conditioned Equivariant Radiance Fields for Infinite 3D Scene Generation CVPR 2024 Ctrl-X: Controlling Structure and Appearance for Text-To-Image Generation Without Guidance NeurIPS 2024 FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Condition CVPR 2024 Shared Autonomy with IDA: Interventional Diffusion Assistance NeurIPS 2024 SimGen: Simulator-conditioned Driving Scene Generation NeurIPS 2024 Towards Text-guided 3D Scene Composition CVPR 2024 CAT: Closed-loop Adversarial Training for Safe End-to-End Driving CoRL 2023 DisCoScene: Spatially Disentangled Generative Radiance Fields for Controllable 3D-Aware Scene Synthesis CVPR 2023 Guarded Policy Optimization with Imperfect Online Demonstrations ICLR 2023 Learning from Active Human Involvement through Proxy Value Propagation NeurIPS 2023 One-Shot Generative Domain Adaptation ICCV 2023 ScenarioNet: Open-Source Platform for Large-Scale Traffic Scenario Simulation and Modeling NeurIPS 2023 Towards Smooth Video Composition ICLR 2023 V2V4Real: A Real-World Large-Scale Dataset for Vehicle-to-Vehicle Cooperative Perception CVPR 2023 3D-Aware Image Synthesis via Learning Structural and Textural Representations CVPR 2022 AutoAlign: Pixel-Instance Feature Aggregation for Multi-Modal 3D Object Detection IJCAI 2022 CoBEVT: Cooperative Bird’s Eye View Semantic Segmentation with Sparse Transformers CoRL 2022 Cross-Model Pseudo-Labeling for Semi-Supervised Action Recognition CVPR 2022 Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization ICLR 2022 Exploit Reward Shifting in Value-Based Deep-RL: Optimistic Curiosity-Based Exploration and Conservative Exploitation via Linear Reward Shaping NeurIPS 2022 Human-AI Shared Control via Policy Dissection NeurIPS 2022 Improving GAN Equilibrium by Raising Spatial Awareness CVPR 2022 Improving GANs with A Dynamic Discriminator NeurIPS 2022 Learning Hierarchical Cross-Modal Association for Co-Speech Gesture Generation CVPR 2022 Learning to Drive by Watching YouTube Videos: Action-Conditioned Contrastive Policy Pretraining ECCV 2022 Semantic-Aware Implicit Neural Audio-Driven Video Portrait Generation ECCV 2022 SimIPU: Simple 2D Image and 3D Point Cloud Unsupervised Pre-training for Spatial-Aware Visual Representations AAAI 2022 Visual Sound Localization in the Wild by Cross-Modal Interference Erasing AAAI 2022 Closed-Form Factorization of Latent Semantics in GANs CVPR 2021 Data-Efficient Instance Generation from Instance Discrimination NeurIPS 2021 Generative Hierarchical Features From Synthesizing Images CVPR 2021 HiABP: Hierarchical Initialized ABP for Unsupervised Representation Learning AAAI 2021 Instance Localization for Self-Supervised Detection Pretraining CVPR 2021 Learning to Simulate Self-driven Particles System with Coordinated Policy Optimization NeurIPS 2021 Multimodal Motion Prediction With Stacked Transformers CVPR 2021 Positional Encoding As Spatial Inductive Bias in GANs CVPR 2021 Safe Driving via Expert Guided Policy Optimization CoRL 2021 TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization ICCV 2021 A Local-to-Global Approach to Multi-Modal Movie Scene Segmentation CVPR 2020 A Unified Framework for Shot Type Classification Based on Subject Centric Lens ECCV 2020 Every Frame Counts: Joint Learning of Video Segmentation and Optical Flow AAAI 2020 Image Processing Using Multi-Code GAN Prior CVPR 2020 In-Domain GAN Inversion for Real Image Editing ECCV 2020 Interpreting the Latent Space of GANs for Semantic Face Editing CVPR 2020 Learning a Decision Module by Imitating Driver’s Control Behaviors CoRL 2020 Neuro-Symbolic Program Search for Autonomous Driving Decision Module Design CoRL 2020 Temporal Pyramid Network for Action Recognition CVPR 2020 TPNet: Trajectory Proposal Network for Motion Prediction CVPR 2020 TransMoMo: Invariance-Driven Unsupervised Video Motion Retargeting CVPR 2020 A Graph-Based Framework to Bridge Movies and Synopses ICCV 2019 Deep Flow-Guided Video Inpainting CVPR 2019 DrivingStereo: A Large-Scale Dataset for Stereo Matching in Autonomous Driving Scenarios CVPR 2019 GAN Dissection: Visualizing and Understanding Generative Adversarial Networks ICLR 2019 Policy Continuation with Hindsight Inverse Dynamics NeurIPS 2019 Reasoning About Human-Object Interactions Through Dual Attention Networks ICCV 2019 Seeing What a GAN Cannot Generate ICCV 2019 Factorizable Net: An Efficient Subgraph-based Framework for Scene Graph Generation ECCV 2018 Interpretable Basis Decomposition for Visual Explanation ECCV 2018 Recurrent Residual Module for Fast Inference in Videos CVPR 2018 Single Image Intrinsic Decomposition without a Single Intrinsic Image ECCV 2018 Temporal Relational Reasoning in Videos ECCV 2018 Unified Perceptual Parsing for Scene Understanding ECCV 2018 Visual Question Generation as Dual Task of Visual Question Answering CVPR 2018 Network Dissection: Quantifying Interpretability of Deep Visual Representations CVPR 2017 Open Vocabulary Scene Parsing ICCV 2017 Person Search With Natural Language Description CVPR 2017 Scene Graph Generation From Objects, Phrases and Region Captions ICCV 2017 Scene Parsing Through ADE20K Dataset CVPR 2017 Learning Deep Features for Discriminative Localization CVPR 2016 Optimization as Estimation with Gaussian Processes in Bandit Settings AISTATS 2016 ConceptLearner: Discovering Visual Concepts From Weakly Labeled Image Collections CVPR 2015 Learning Deep Features for Scene Recognition using Places Database NeurIPS 2014 Measuring Crowd Collectiveness CVPR 2013