@inproceedings{tu2026hint2gen,
  title={Hint2Gen: Bridging Understanding and Generation via Code-structured Hints},
  author={Tu, Yuanpeng and Chen, Yunpeng and Chen, Xi and Li, Liang and Zhao, Hengshuang},
  booktitle={CVPR},
  year={2026}
}

@inproceedings{tu2026temporal,
  title={Temporal Equilibrium MeanFlow: Bridging the Scale Gap for One-Step Generation},
  author={Tu, Yuanpeng and Chen, Yunpeng and Zhang, Xinyu and Liao, Chao and Zhao, Hengshuang},
  booktitle={CVPR},
  year={2026}
}

@inproceedings{wang2026gdro,
  title={GDRO: Group-level Reward Post-training Suitable for Diffusion Models},
  author={Wang, Yiyang and Chen, Xi and Xu, Xiaogang and Liu, Yu and Zhao, Hengshuang},
  booktitle={CVPR},
  year={2026}
}

@inproceedings{ding2026surf,
  title={SURF: Signature-retained Fast Video Generation},
  author={Ding, Kaixin and Chen, Xi and Ji, Sihui and Gao, Yuan and Hou, Liang and Tao, Xin and Zhao, Hengshuang},
  booktitle={CVPR},
  year={2026}
}

@inproceedings{liu2026drivepi,
  title={DrivePI: Spatial-aware 4D MLLM for Unified Autonomous Driving Understanding, Perception, Prediction and Planning},
  author={Liu, Zhe and Huang, Runhui and Yang, Rui and Yan, Siming and Wang, Zining and Hou, Lu and Lin, Di and Bai, Xiang and Zhao, Hengshuang},
  booktitle={CVPR},
  year={2026}
}

@inproceedings{yang2026geniedrive,
  title={GenieDrive: Towards Physics-Aware Driving World Model with 4D Occupancy Guided Video Generation},
  author={Yang, Zhenya and Liu, Zhe and Lu, Yuxiang and Hou, Liping and Miao, Chenxuan and Peng, Siyi and Feng, Bailan and Bai, Xiang and Zhao, Hengshuang},
  booktitle={CVPR},
  year={2026}
}

@inproceedings{tan2026synmotion,
  title={Synmotion: Semantic-visual adaptation for motion customized video generation},
  author={Tan, Shuai and Gong, Biao and Wei, Yujie and Zhang, Shiwei and Liu, Zhuoxin and Wang, Yan and Zheng, Kecheng and Zhu, Xing and Shen, Yujun, and Zhao, Hengshuang},
  booktitle={CVPR},
  year={2026}
}

@inproceedings{yang2026in,
  title={In Pursuit of Pixel Supervision for Visual Pre-training},
  author={Yang, Lihe and Li, Shang-Wen and Li, Yang and Lei, Xinjie and Wang, Dong and Mohamed, Abdelrahman and Xie, Saining and Zhao, Hengshuang and He, Kaiming and Xu, Hu},
  booktitle={CVPR},
  year={2026}
}

@inproceedings{wu2026recedit,
  title={RecEdit-Drive: 3D Reconstruction-Guided Spatiotemporal Video Editing for Autonomous Driving Scenes},
  author={Wu, Yipeng and Wang, Xin and Yang, Chenghan and Wang, Chong and Wu, Dongdong and Su, Wanchao and Zhao, Hengshuang and Feng, Wei and Yang, Kairui and Lin, Di},
  booktitle={CVPR},
  year={2026}
}

@inproceedings{yang2026sigliphd,
  title={SigLIP-HD by Fine-to-Coarse Supervision},
  author={Yang, Lihe and Zhao, Zhen and Zhao, Hengshuang},
  booktitle={ICLR},
  year={2026}
}

@inproceedings{qi2026gpt4scene,
  title={GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models},
  author={Qi, Zhangyang and Zhang, Zhixiong and Fang, Ye and Wang, Jiaqi and Zhao, Hengshuang},
  booktitle={ICLR},
  year={2026}
}

@inproceedings{lai2026minio3,
  title={Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search},
  author={Lai, Xin and Li, Junyi and Li, Wei and Liu, Tao and Li, Tianjian and Zhao, Hengshuang},
  booktitle={ICLR},
  year={2026}
}

@inproceedings{lao2026less,
  title={Less Gaussians, Texture More: 4K Feed-Forward Textured Splatting},
  author={Lao, Yixing and Bai, Xuyang and Wu, Xiaoyang and Yan, Nuoyuan and Luo, Zixin and Fang, Tian and Nahmias, Jean-Daniel and Tsin, Yanghai and Li, Shiwei Li and Zhao, Hengshuang},
  booktitle={ICLR},
  year={2026}
}

@inproceedings{wang2026depth,
  title={Depth Anything with Any Prior},
  author={Wang, Zehan and Chen, Siyu and Yang, Lihe and Wang, Jialei and Zhang, Ziang and Zhao, Hengshuang and Zhao, Zhou},
  booktitle={ICLR},
  year={2026}
}

@inproceedings{wang2025spatialhand,
  title={SpatialHand: Generative Object Manipulation from 3D Prespective},
  author={Wang, Zehan and Wang, Jialei and Chen, Siyu and Zhang, Ziang and Liu, Luping and Cheng, Xize and Pan, Kaihang and Zhao, Hengshuang and Zhou, Zhao},
  booktitle={ICLR},
  year={2026}
}

@inproceedings{qian2026animeready,
  title={Anime-Ready: Controllable 3D Anime Character Generation with Body-Aligned Component-Wise Garment Modeling},
  author={Qian, Jiachen and Yang, Hongye and Lin, Youtian and Zhao, Tianhao and Zhang, Feihu and Yao, Yao and Zhao, Hengshuang},
  booktitle={ICLR},
  year={2026}
}

@inproceedings{qi2026game,
  title={Game Ground Bench: Probing the Limits of LVLMs in Complex Semantic Grounding Across Game Universes},
  author={Qi, Zhangyang and Li, Jinsong and Wu, Hongjian and Wang, Jiaqi and Zhao, Hengshuang},
  booktitle={AAAI},
  year={2026}
}

@article{zheng2026causal,
  title={Causal Prompts for Open-vocabulary Video Instance Segmentation},
  author={Zheng, Rongkun and Qi, Lu and Chen, Xi and Wang, Yi and Wang, Kun and Qiao, Yu and Zhao, Hengshuang},
  journal={TPAMI},
  year={2026}
}

@article{tu2026memory,
  title={Memory Consistency Guided Divide-and-Conquer Learning for Generalized Category Discovery},
  author={Tu, Yuanpeng and Zhong, Zhun and Li, Yuxi and Zhao, Hengshuang},
  journal={IJCV},
  year={2026}
}

@article{wu2026liquid,
  title={Liquid: Language Models are Scalable and Unified Multi-modal Generators},
  author={Wu, Junfeng and Jiang, Yi and Ma, Chuofan and Liu, Yuliang and Zhao, Hengshuang and Yuan, Zehuan and Bai, Song and Bai, Xiang},
  journal={IJCV},
  year={2026}
}

@inproceedings{tu2025playerone,
  title={PlayerOne: Egocentric World Simulator},
  author={Tu, Yuanpeng and Luo, Hao and Chen, Xi and Bai, Xiang and Wang, Fan and Zhao, Hengshuang},
  booktitle={NeurIPS},
  year={2025}
}

@inproceedings{zhang2025concerto,
  title={Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations},
  author={Zhang, Yujia and Wu, Xiaoyang and Lao, Yixing and Wang, Chengyao and Tian, Zhuotao and Wang, Naiyan and Zhao, Hengshuang},
  booktitle={NeurIPS},
  year={2025}
}

@inproceedings{chen2025mico,
  title={MiCo: Multi-image Contrast for Reinforcement Visual Reasoning},
  author={Chen, Xi and Zhu, Mingkang and Liu, Shaoteng and Wu, Xiaoyang and Xu, Xiaogang and Liu, Yu and Bai, Xiang and Zhao, Hengshuang},
  booktitle={NeurIPS},
  year={2025}
}

@inproceedings{zheng2025segvar,
  title={Seg-VAR:Image Segmentation with Visual Autoregressive Modeling},
  author={Zheng, Rongkun and Qi, Lu and Chen, Xi and Wang, Yi and Wang, Kun and Qiao, Yu and Zhao, Hengshuang},
  booktitle={NeurIPS},
  year={2025}
}

@inproceedings{miao2025rose,
  title={ROSE: Remove Objects with Side Effects in Videos},
  author={Miao, Chenxuan and Feng, Yutong and Zeng, Jianshu and Gao, Zixiang and Liu, Hantang and Yan, Yunfeng and Qi, Donglian and Chen, Xi and Wang, Bin and Zhao, Hengshuang},
  booktitle={NeurIPS},
  year={2025}
}

@inproceedings{yang2025visionthink,
  title={VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning},
  author={Yang, Senqiao and Li, Junyi and Lai, Xin and Yu, Bei and Zhao, Hengshuang and Jia, Jiaya},
  booktitle={NeurIPS},
  year={2025}
}

@inproceedings{wang2025orientv2,
  title={Orient Anything V2: Unifying Orientation and Rotation Understanding},
  author={Wang, Zehan and Zhang, Ziang and Xu, Jiayang and Wang, Jialei and Pang, Tianyu and Du, Chao and Zhao, Hengshuang and Zhao, Zhou},
  booktitle={NeurIPS},
  year={2025}
}

@inproceedings{huang2025litereality,
  title={LiteReality: Graphics-Ready 3D Scene Reconstruction from RGB-D Scans},
  author={Huang, Zhening and Wu, Xiaoyang and Zhong, Fangcheng and Zhao, Hengshuang and Nie{\ss}ner, Matthias and Lasenby, Joan},
  booktitle={NeurIPS},
  year={2025}
}

@inproceedings{chu2025wanmove,
  title={Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance},
  author={Chu, Ruihang and He, Yefei and Chen, Zhekai and Zhang, Shiwei and Xu, Xiaogang and Xia, Bin and Wang, Dingdong and Yi, Hongwei and Liu, Xihui and Zhao, Hengshuang and Liu, Yu and Zhang, Yingya and Yang, Yujiu},
  booktitle={NeurIPS},
  year={2025}
}

@inproceedings{wang2025genspace,
  title={GenSpace: Benchmarking Spatially-Aware Image Generation},
  author={Wang, Zehan and Xu, Jiayang and Zhang, Ziang and Pang, Tianyu and Du, Chao and Zhao, Hengshuang and Zhao, Zhou},
  booktitle={NeurIPSDB},
  year={2025}
}

@inproceedings{wang2025diffcamera,
  title={DiffCamera: Arbitrary Refocusing on Images},
  author={Wang, Yiyang and Chen, Xi and Xu, Xiaogang and Liu, Yu and Zhao, Hengshuang},
  booktitle={SIGGRAPHAsia},
  year={2025}
}

@inproceedings{zhu2025enhancing,
  title={Effective LLM Knowledge Learning via Model Generalization},
  author={Zhu, Mingkang and Chen, Xi and Wang, Zhongdao and Yu, Bei and Zhao, Hengshuang and Jia, Jiaya},
  booktitle={EMNLP},
  year={2025}
}

@inproceedings{zhang2025stabledepth,
  title={StableDepth: Scene-Consistent and Scale-Invariant Monocular Depth},
  author={Zhang, Zheng and Yang, Lihe and Yang, Tianyu and Yu, Chaohui and Guo, Xiaoyang and Lao, Yixing and Zhao, Hengshuang},
  booktitle={ICCV},
  year={2025}
}

@inproceedings{wang2025diffdoctor,
  title={DiffDoctor: Diagnosing Image Diffusion Models Before Treating},
  author={Wang, Yiyang and Chen, Xi and Xu, Xiaogang and Ji, Sihui and Liu, Yu and Shen, Yujun and Zhao, Hengshuang},
  booktitle={ICCV},
  year={2025}
}

@inproceedings{zheng2025villa,
  title={ViLLa: Video Reasoning Segmentation with Large Language Model},
  author={Zheng, Rongkun and Qi, Lu and Chen, Xi and Wang, Yi and Wang, Kun and Qiao, Yu and Zhao, Hengshuang},
  booktitle={ICCV},
  year={2025}
}

@inproceedings{zhao2025disco,
  title={DisCo: Towards Distinct and Coherent Visual Encapsulation in Video MLLMs},
  author={Zhao, Jiahe and Zheng, Rongkun and Wang, Yi and Wang, Helin and Zhao, Hengshuang},
  booktitle={ICCV},
  year={2025}
}

@inproceedings{zhou2025hermes,
  title={HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation},
  author={Zhou, Xin and Liang, Dingkang and Tu, Sifan and Chen, Xiwu and Ding, Yikang and Zhang, Dingyuan and Tan, Feiyang and Zhao, Hengshuang and Bai, Xiang},
  booktitle={ICCV},
  year={2025}
}

@inproceedings{tu2025videoanydoor,
  title={VideoAnydoor: High-fidelity Video Object Insertion with Precise Motion Control},
  author={Tu, Yuanpeng and Luo, Hao and Chen, Xi and Ji, Sihui and Bai, Xiang and Zhao, Hengshuang},
  booktitle={SIGGRAPH},
  year={2025}
}

@inproceedings{ji2025layerflow,
  title={LayerFlow: A Unified Model for Layer-aware Video Generation},
  author={Ji, Sihui and Luo, Hao and Chen, Xi and Tu, Yuanpeng and Wang, Yiyang and Zhao, Hengshuang},
  booktitle={SIGGRAPH},
  year={2025}
}

@inproceedings{ji2024fashioncomposer,
  title={FashionComposer: Compositional Fashion Image Generation},
  author={Ji, Sihui and Wang, Yiyang and Chen, Xi and Xu, Xiaogang and Luo, Hao and Zhao, Hengshuang},
  booktitle={SIGGRAPH},
  year={2025}
}

@inproceedings{tu2025dreammask,
  title={DreamMask: Boosting Open-vocabulary Panoptic Segmentation with Synthetic Data},
  author={Tu, Yuanpeng and Chen, Xi and Lim, Ser-Nam and Zhao, Hengshuang},
  booktitle={SIGGRAPH},
  year={2025}
}

@inproceedings{li2025vip,
  title={VIP: Vision Instructed Pre-training for Robotic Manipulation},
  author={Li, Zhuoling and Ren, Liangliang and Yang, Jinrong and Zhao, Yong and Wu, Xiaoyang and Xu, Zhenhua and Bai, Xiang and Zhao, Hengshuang},
  booktitle={ICML},
  year={2025}
}

@inproceedings{li2025larm,
  title={LARM: Large Auto-Regressive Model for Long-Horizon Embodied Intelligence},
  author={Li, Zhuoling and Xu, Xiaogang and Xu, Zhenhua and Lim, SerNam and Zhao, Hengshuang},
  booktitle={ICML},
  year={2025}
}

@inproceedings{yang2025haplovl,
  title={HaploVL: A Single-Transformer Baseline for Multi-Modal Understanding},
  author={Yang, Rui and Song, Lin and Xiao, Yicheng and Huang, Runhui and Ge, Yixiao and Shan, Ying and Zhao, Hengshuang},
  booktitle={ICML},
  year={2025}
}

@inproceedings{liao2025bood,
  title={BOOD: Boundary-based Out-Of-Distribution Data Generation},
  author={Liao, Qilin and Yang, Shuo and Zhao, Bo and Luo, Ping and Zhao, Hengshuang},
  booktitle={ICML},
  year={2025}
}

@inproceedings{wang2025orient,
  title={Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models},
  author={Wang, Zehan and Zhang, Ziang and Pang, Tianyu and Du, Chao and Zhao, Hengshuang and Zhao, Zhou},
  booktitle={ICML},
  year={2025}
}

@inproceedings{zhu2025tgdpo,
  title={TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization},
  author={Zhu, Mingkang and Chen, Xi and Wang, Zhongdao and Yu, Bei and Zhao, Hengshuang and Jia, Jiaya},
  booktitle={ICML},
  year={2025}
}

@inproceedings{chen2025unireal,
  title={UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics},
  author={Chen, Xi and Zhang, Zhifei and Zhang, He and Zhou, Yuqian and Kim, Soo Ye and Liu, Qing and Li, Yijun and Zhang, Jianming and Zhao, Nanxuan and Wang, Yilin and others},
  booktitle={CVPR},
  year={2025}
}

@inproceedings{xu2025drivegpt4v2,
  title={DriveGPT4-V2: Harnessing Large Language Model Capabilities for Enhanced Closed-Loop Autonomous Driving},
  author={Xu, Zhenhua and Bai, Yan and Zhang, Yujia and Li, Zhuoling and Xia, Fei and and Wong, Kenneth KY and Wang, Jianqiang and Zhao, Hengshuang},
  booktitle={CVPR},
  year={2025}
}

@inproceedings{wu2025sonata,
  title={Sonata: Self-Supervised Learning of Reliable Point Representations},
  author={Wu, Xiaoyang and DeTone, Daniel and Frost, Duncan and Shen, Tianwei and Xie, Chris and Yang, Nan and Engel, Jakob and Newcombe, Richard and Zhao, Hengshuang and Straub, Julian},
  booktitle={CVPR},
  year={2025}
}

@inproceedings{wang2025spatialclip,
  title={SpatialCLIP: Learning 3D-aware Image Representations from Spatially Discriminative Language},
  author={Wang, Zehan and zhou, Sashuai and He, Shaoxuan and Huang, Haifeng and Yang, Lihe and Zhang, Ziang and Cheng, Xize and Ji, Shengpeng and Jin, Tao and Zhao, Hengshuang and Zhao, Zhou},
  booktitle={CVPR},
  year={2025}
}

@inproceedings{cao2025panda,
  title={PanDA: Towards Panoramic Depth Anything with Unlabeled Panoramas and Mobius Spatial Augmentation},
  author={Cao, Zidong and Zhu, Jinjing and Zhang, Weiming and Ai, Hao and Bai, Haotian and Zhao, Hengshuang and Wang, Lin},
  booktitle={CVPR},
  year={2025}
}

@inproceedings{yuan2025empowering,
  title={Empowering Large Language Models with 3D Situation Awareness},
  author={Yuan, Zhihao and Peng, Yibo and Ren, Jinke and Liao, Yinghong and Han, Yatong and Feng, Chun-Mei and Zhao, Hengshuang and Li, Guanbin and Cui, Shuguang and Li, Zhen},
  booktitle={CVPR},
  year={2025}
}

@inproceedings{huang2025hires,
  title={Hires-llava: Restoring fragmentation input in high-resolution large vision-language models},
  author={Huang, Runhui and Ding, Xinpeng and Wang, Chunwei and Han, Jianhua and Liu, Yulong and Zhao, Hengshuang and Xu, Hang and Hou, Lu and Zhang, Wei and Liang, Xiaodan},
  booktitle={CVPR},
  year={2025}
}

@inproceedings{chen2025emova,
  title={Emova: Empowering language models to see, hear and speak with vivid emotions},
  author={Chen, Kai and Gou, Yunhao and Huang, Runhui and Liu, Zhili and Tan, Daxin and Xu, Jing and Wang, Chunwei and Zhu, Yi and Zeng, Yihan and Yang, Kuo and others},
  booktitle={CVPR},
  year={2025}
}

@inproceedings{wang2025omnibind,
  title={Omnibind: Large-scale omni multimodal representation via binding spaces},
  author={Wang, Zehan and Zhang, Ziang and Zhang, Hang and Liu, Luping and Huang, Rongjie and Cheng, Xize and Zhao, Hengshuang and Zhao, Zhou},
  booktitle={ICLR},
  year={2025}
}

@article{li2025towards,
  title={Towards Unified 3D Object Detection via Algorithm and Data Unification},
  author={Li, Zhuoling and Xu, Xiaogang and Lim, SerNam and Zhao, Hengshuang},
  journal={TPAMI},
  year={2025}
}

@article{chen2025anydoor,
  title={AnyDoor: Zero-shot Image Customization with Region-to-region Reference},
  author={Chen, Xi and Huang, Lianghua and Liu, Yu and Shen, Yujun and Zhao, Deli and Zhao, Hengshuang},
  journal={TPAMI},
  year={2025}
}

@article{yang2025unimatch,
  title={Unimatch v2: Pushing the limit of semi-supervised semantic segmentation},
  author={Yang, Lihe and Zhao, Zhen and Zhao, Hengshuang},
  journal={TPAMI},
  year={2025}
}

@article{qi2025gpt4point++,
  title={GPT4Point++: Advancing Unified Point-Language Understanding and Generation},
  author={Qi, Zhangyang and Fang, Ye and Sun, Zeyi and Wu, Xiaoyang and Wu, Tong and Wang, Jiaqi and Lin, Dahua and Zhao, Hengshuang},
  journal={TPAMI},
  year={2025}
}

@article{yang2025dreamcomposer++,
  title={DreamComposer++: Empowering Diffusion Models with Multi-View Conditions for 3D Content Generation},
  author={Yang, Yunhan and Chen, Shuo and Huang, Yukun and Wu, Xiaoyang and Guo, Yuan-Chen and Lam, Edmund Y and Zhao, Hengshuang and He, Tong and Liu, Xihui},
  journal={TPAMI},
  year={2025}
}

@article{zhu2025ponderv2,
  title={PonderV2: Improved 3D Representation with A Universal Pre-training Paradigm},
  author={Zhu, Haoyi and Yang, Honghui and Wu, Xiaoyang and Huang, Di and Zhang, Sha and He, Xianglong and Zhao, Hengshuang and Shen, Chunhua and Qiao, Yu and He, Tong and others},
  journal={TPAMI},
  year={2025}
}

@inproceedings{yang2024depthv2,
  title={Depth Anything V2},
  author={Yang, Lihe and Kang, Bingyi and Huang, Zilong and Zhao, Zhen and Xu, Xiaogang and Feng, Jiashi and Zhao, Hengshuang},
  booktitle={NeurIPS},
  year={2024}
}

@inproceedings{chen2024zero,
  title={Zero-shot Image Editing with Reference Imitation},
  author={Chen, Xi and Feng, Yutong and Chen, Mengting and Wang, Yiyang and Zhang, Shilong and Liu, Yu and Shen, Yujun and Zhao, Hengshuang},
  booktitle={NeurIPS},
  year={2024}
}

@inproceedings{lao2024lit,
  title={LiT: Unifying LiDAR "Languages" with LiDAR Translator},
  author={Lao, Yixing and Tang, Tao and Wu, Xiaoyang and Chen, Peng and Yu, Kaicheng and Zhao, Hengshuang},
  booktitle={NeurIPS},
  year={2024}
}

@inproceedings{zheng2024syncvis,
  title={SyncVIS: Synchronized Video Instance Segmentation},
  author={Zheng, Rongkun and Qi, Lu and Chen, Xi and Wang, Yi and Wang, Kun and Qiao, Yu and Zhao, Hengshuang},
  booktitle={NeurIPS},
  year={2024}
}

@inproceedings{wang2024one,
  title={One for All: Multi-Domain Joint Training for Point Cloud Based 3D Object Detection},
  author={Wang, Zhenyu and Li, Yali and Zhao, Hengshuang and Wang, Shengjin},
  booktitle={NeurIPS},
  year={2024}
}

@inproceedings{liu2024lion,
  title={LION: Linear Group RNN for 3D Object Detection in Point Clouds},
  author={Liu, Zhe and Hou, Jinghua and Wang, Xinyu and Ye, Xiaoqing and Wang, Jingdong and Zhao, Hengshuang and Bai, Xiang},
  booktitle={NeurIPS},
  year={2024}
}

@inproceedings{chen2024livephoto,
  title={LivePhoto: Real Image Animation with Text-guided Motion Control},
  author={Chen, Xi and Liu, Zhiheng and Chen, Mengting and Feng, Yutong and Liu, Yu and Shen, Yujun and Zhao, Hengshuang},
  booktitle={ECCV},
  year={2024}
}

@inproceedings{zhang2024pixel,
  title={Pixel-GS: Density Control with Pixel-aware Gradient for 3D Gaussian Splatting},
  author={Zhang, Zheng and Hu, Wenbo and Lao, Yixing and He, Tong and Zhao, Hengshuang},
  booktitle={ECCV},
  year={2024}
}

@inproceedings{xu2024insmapper,
  title={InsMapper: Exploring Inner-instance Information for Vectorized HD Mapping},
  author={Xu, Zhenhua and Wong, Kwan-Yee K and Zhao, Hengshuang},
  booktitle={ECCV},
  year={2024}
}

@inproceedings{wang2024ov,
  title={OV-Uni3DETR: Towards Unified Open-Vocabulary 3D Object Detection via Cycle-Modality Propagation},
  author={Wang, Zhenyu and Li, Yali and Liu, Taichi and Zhao, Hengshuang and Wang, Shengjin},
  booktitle={ECCV},
  year={2024}
}

@inproceedings{zhu2024logosticker,
  title={LogoSticker: Inserting Logos into Diffusion Models for Customized Generation},
  author={Zhu, Mingkang and Chen, Xi and Wang, Zhongdao and Zhao, Hengshuang and Jia, Jiaya},
  booktitle={ECCV},
  year={2024}
}

@inproceedings{huang2024openins3d,
  title={OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentation},
  author={Huang, Zhening and Wu, Xiaoyang and Chen, Xi and Zhao, Hengshuang and Zhu, Lei and Lasenby, Joan},
  booktitle={ECCV},
  year={2024}
}

@inproceedings{tang2024mind,
  title={Mind the Interference: Retaining Pre-trained Knowledge in Parameter Efficient Continual Learning of Vision-Language Models},
  author={Tang, Longxiang and Tian, Zhuotao and Li, Kai and He, Chunming and Zhou, Hantao and Zhao, Hengshuang and Li, Xiu and Jia, Jiaya},
  booktitle={ECCV},
  year={2024}
}

@article{yang2024language,
  title={Language-aware vision transformer for referring segmentation},
  author={Yang, Zhao and Wang, Jiaqi and Ye, Xubing and Tang, Yansong and Chen, Kai and Zhao, Hengshuang and Torr, Philip HS},
  journal={TPAMI},
  year={2024}
}

@article{wang2024unidetector,
  title={UniDetector: Towards Universal Object Detection with Heterogeneous Supervision},
  author={Wang, Zhenyu and Li, Yali and Chen, Xi and Lim, Ser-Nam and Torralba, Antonio and Zhao, Hengshuang and Wang, Shengjin},
  journal={TPAMI},
  year={2024}
}

@article{xu2024drivegpt4,
  title={{DriveGPT4}: Interpretable End-to-end Autonomous Driving via Large Language Model},
  author={Xu, Zhenhua and Zhang, Yujia and Xie, Enze and Zhao, Zhen and Guo, Yong and Wong, Kenneth KY and Li, Zhenguo and Zhao, Hengshuang},
  journal={RA-L},
  year={2024}
}

@article{li2024grouplane,
  title={{GroupLane}: End-to-End 3D Lane Detection with Channel-wise Grouping},
  author={Li, Zhuoling and Han, Chunrui and Ge, Zheng and Yang, Jinrong and Yu, En and Wang, Haoqian and Zhang, Xiangyu and Zhao, Hengshuang},
  journal={RA-L},
  year={2024}
}

@inproceedings{yang2024depth,
  title={Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data},
  author={Yang, Lihe and Kang, Bingyi and Huang, Zilong and Xu, Xiaogang and Feng, Jiashi and Zhao, Hengshuang},
  booktitle={CVPR},
  year={2024}
}

@inproceedings{chen2024anydoor,
  title={Anydoor: Zero-shot Object-level Image Customization},
  author={Chen, Xi and Huang, Lianghua and Liu, Yu and Shen, Yujun and Zhao, Deli and Zhao, Hengshuang},
  booktitle={CVPR},
  year={2024}
}

@inproceedings{wu2024point,
  title={Point Transformer V3: Simpler, Faster, Stronger},
  author={Wu, Xiaoyang and Jiang, Li and Wang, Peng-Shuai and Liu, Zhijian and Liu, Xihui and Qiao, Yu and Ouyang, Wanli and He, Tong and Zhao, Hengshuang},
  booktitle={CVPR},
  year={2024}
}

@inproceedings{wu2024towards,
  title={Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training},
  author={Wu, Xiaoyang and Tian, Zhuotao and Wen, Xin and Peng, Bohao and Liu, Xihui and Yu, Kaicheng and Zhao, Hengshuang},
  booktitle={CVPR},
  year={2024}
}

@inproceedings{qi2024gpt4point,
  title={GPT4Point: A Unified Framework for Point-Language Understanding and Generation},
  author={Qi, Zhangyang and Fang, Ye and Sun, Zeyi and Wu, Xiaoyang and Wu, Tong and Wang, Jiaqi and Lin, Dahua and Zhao, Hengshuang},
  booktitle={CVPR},
  year={2024}
}

@inproceedings{li2024unimode,
  title={UniMODE: Universal Monocular 3D Object Detection},
  author={Li, Zhuoling and Xu, Xiaogang and Lim, Ser-Nam and Zhao, Hengshuang},
  booktitle={CVPR},
  year={2024}
}

@inproceedings{wang2024groupcontrast,
  title={GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D Understanding},
  author={Wang, Chengyao and Jiang, Li and Wu, Xiaoyang and Tian, Zhuotao and Peng, Bohao and Zhao, Hengshuang and Jia, Jiaya},
  booktitle={CVPR},
  year={2024}
}

@inproceedings{peng2024omni,
  title={Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation},
  author={Peng, Bohao and Wu, Xiaoyang and Jiang, Li and Chen, Yukang and Zhao, Hengshuang and Tian, Zhuotao and Jia, Jiaya},
  booktitle={CVPR},
  year={2024}
}

@inproceedings{yang2023dreamcomposer,
  title={DreamComposer: Controllable 3D Object Generation via Multi-View Conditions},
  author={Yang, Yunhan and Huang, Yukun and Wu, Xiaoyang and Guo, Yuan-Chen and Zhang, Song-Hai and Zhao, Hengshuang and He, Tong and Liu, Xihui},
  booktitle={CVPR},
  year={2024}
}

@inproceedings{yuan2024visual,
  title={Visual Programming for Zero-shot Open-Vocabulary 3D Visual Grounding},
  author={Yuan, Zhihao and Ren, Jinke and Feng, Chun-Mei and Zhao, Hengshuang and Cui, Shuguang and Li, Zhen},
  booktitle={CVPR},
  year={2024}
}

@inproceedings{yang2024unipad,
  title={Unipad: A universal pre-training paradigm for autonomous driving},
  author={Yang, Honghui and Zhang, Sha and Huang, Di and Wu, Xiaoyang and Zhu, Haoyi and He, Tong and Tang, Shixiang and Zhao, Hengshuang and Qiu, Qibo and Lin, Binbin and others},
  booktitle={CVPR},
  year={2024}
}

@inproceedings{clan2024influencer,
  title={Influencer Backdoor Attack on Semantic Segmentation},
  author={Lan, Haoheng and Gu, Jindong and Torr, Philip and Zhao, Hengshuang},
  booktitle={ICLR},
  year={2024}
}

@inproceedings{qi2024ocbev,
  title={OCBEV: Object-Centric BEV Transformer for Multi-View 3D Object Detection},
  author={Qi, Zhangyang and Wang, Jiaqi and Wu, Xiaoyang and Zhao, Hengshuang},
  booktitle={3DV},
  year={2024}
}

@inproceedings{yang2023freemask,
  title={Freemask: Synthetic images with dense annotations make stronger segmentation models},
  author={Yang, Lihe and Xu, Xiaogang and Kang, Bingyi and Shi, Yinghuan and Zhao, Hengshuang},
  booktitle={NeurIPS},
  year={2023}
}

@inproceedings{wang2023uni3detr,
  title={Uni3DETR: Unified 3D Detection Transformer},
  author={Wang, Zhenyu and Li, Yali and Chen, Xi and Zhao, Hengshuang and Wang, Shengjin},
  booktitle={NeurIPS},
  year={2023}
}

@inproceedings{zheng2023tmtvis,
  title={TMT-VIS: Taxonomy-aware Multi-dataset Joint Training for Video Instance Segmentation},
  author={Zheng, Rongkun and Qi, Lu and Chen, Xi and Wang, Yi and Wang, Kun and Qiao, Yu and Zhao, Hengshuang},
  booktitle={NeurIPS},
  year={2023}
}

@inproceedings{lao2023corresnerf,
  title={CorresNeRF: Image Correspondence Priors for Neural Radiance Fields},
  author={Lao, Yixing and Xu, Xiaogang and Cai, Zhipeng and Liu, Xihui and Zhao, Hengshuang},
  booktitle={NeurIPS},
  year={2023}
}

@inproceedings{chen2023open,
  title={Open-vocabulary Panoptic Segmentation with Embedding Modulation},
  author={Chen, Xi and Li, Shuang and Lim, Ser-Nam and Torralba, Antonio and Zhao, Hengshuang},
  booktitle={ICCV},
  year={2023}
}

@inproceedings{yang2023shrinking,
  title={Shrinking Class Space for Enhanced Certainty in Semi-Supervised Learning},
  author={Yang, Lihe and Zhao, Zhen and Qi, Lei and Qiao, Yu and Shi, Yinghuan and Zhao, Hengshuang},
  booktitle={ICCV},
  year={2023}
}

@inproceedings{zhou2023bt2,
  title={$ BT\^{} 2$: Backward-compatible Training with Basis Transformation},
  author={Zhou, Yifei and Li, Zilu and Shrivastava, Abhinav and Zhao, Hengshuang and Torralba, Antonio and Tian, Taipeng and Lim, Ser-Nam},
  booktitle={ICCV},
  year={2023}
}

@inproceedings{yang2023sam3d,
  title={Sam3d: Segment anything in 3d scenes},
  author={Yang, Yunhan and Wu, Xiaoyang and He, Tong and Zhao, Hengshuang and Liu, Xihui},
  booktitle={ICCVW},
  year={2023}
}

@inproceedings{wu2023masked,
  title={Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learning},
  author={Wu, Xiaoyang and Wen, Xin and Liu, Xihui and Zhao, Hengshuang},
  booktitle={CVPR},
  year={2023}
}

@inproceedings{wang2023detecting,
  title={Detecting Everything in the Open World: Towards Universal Object Detection},
  author={Wang, Zhenyu and Li, Yali and Chen, Xi and Lim, Ser-Nam and Torralba, Antonio and Zhao, Hengshuang and Wang, Shengjin},
  booktitle={CVPR},
  year={2023}
}

@inproceedings{chen2023mod,
  title={Mod-Squad: Designing Mixtures of Experts As Modular Multi-Task Learners},
  author={Chen, Zitian and Shen, Yikang and Ding, Mingyu and Chen, Zhenfang and Zhao, Hengshuang and Learned-Miller, Erik G and Gan, Chuang},
  booktitle={CVPR},
  year={2023}
}

@inproceedings{yang2023semantics,
  title={Semantics-Aware Dynamic Localization and Refinement for Referring Image Segmentation},
  author={Yang, Zhao and Wang, Jiaqi and Tang, Yansong and Chen, Kai and Zhao, Hengshuang and Torr, Philip HS},
  booktitle={AAAI},
  year={2023}
}

@inproceedings{xu2023universal,
  title={Universal adaptive data augmentation},
  author={Xu, Xiaogang and Zhao, Hengshuang},
  booktitle={IJCAI},
  year={2023}
}

@article{yu2023physformer++,
  title={PhysFormer++: Facial Video-Based Physiological Measurement with SlowFast Temporal Difference Transformer},
  author={Yu, Zitong and Shen, Yuming and Shi, Jingang and Zhao, Hengshuang and Cui, Yawen and Zhang, Jiehua and Torr, Philip and Zhao, Guoying},
  journal={IJCV},
  year={2023}
}

@inproceedings{wu2022point,
  title={Point Transformer V2: Grouped Vector Attention and Partition-based Pooling},
  author={Wu, Xiaoyang and Lao, Yixing and Jiang, Li and Liu, Xihui and Zhao, Hengshuang},
  booktitle={NeurIPS},
  year={2022}
}

@inproceedings{xu2022mtformer,
  title={{MTFormer}: Multi-Task Learning via Transformer and Cross-Task Reasoning},
  author={Xu, Xiaogang and Zhao, Hengshuang and Vineet, Vibhav and Lim, Ser-Nam and Torralba, Antonio},
  booktitle={ECCV},
  year={2022}
}

@inproceedings{gu2022segpgd,
  title={{SegPGD}: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustness},
  author={Gu, Jindong Gu and Zhao, Hengshuang and Tresp, Volker and Torr, Philip},
  booktitle={ECCV},
  year={2022}
}

@inproceedings{lai2022decouplenet,
  title={{DecoupleNet}: Decoupled Network for Domain Adaptive Semantic Segmentation},
  author={Lai, Xin and Tian, Zhuotao and Xu, Xiaogang and Chen, Yingcong and Liu, Shu and Zhao, Hengshuang and Wang, Liwei and Jia, Jiaya},
  booktitle={ECCV},
  year={2022}
}

@inproceedings{gao2022towards,
  title={Towards Visual Social Navigation in Photo-realistic Indoor Scenes},
  author={Gao, Feng and Zhao, Hengshuang and Wang, Yu},
  booktitle={RSSW},
  year={2022}
}

@inproceedings{chen2022focalclick,
  title={FocalClick: Towards Practical Interactive Image Segmentation},
  author={Chen, Xi and Zhao, Zhiyan and Zhang, Yilei and Duan, Manni and Qi, Donglian and Zhao, Hengshuang},
  booktitle={CVPR},
  year={2022}
}

@inproceedings{yang2022lavt,
  title={LAVT: Language-Aware Vision Transformer for Referring Image Segmentation},
  author={Yang, Zhao and Wang, Jiaqi and Tang, Yansong and Chen, Kai and Zhao, Hengshuang and Torr, Philip HS},
  booktitle={CVPR},
  year={2022}
}

@inproceedings{tian2022gfsseg,
  title={Generalized Few-shot Semantic Segmentation},
  author={Tian, Zhuotao and Lai, Xin and Jiang, Li and Shu, Michelle and Zhao, Hengshuang and Jia, Jiaya},
  booktitle={CVPR},
  year={2022}
}

@inproceedings{yu2022physformer,
  title={PhysFormer: Facial Video-based Physiological Measurement with Temporal Difference Transformer},
  author={Yu, Zitong and Shen, Yuming and Shi, Jingang and Zhao, Hengshuang and Torr, Philip and Zhao, Guoying},
  booktitle={CVPR},
  year={2022}
}

@inproceedings{lai2022stratified,
  title={Stratified Transformer for 3D Point Cloud Segmentation},
  author={Lai, Xin and Liu, Jianhui and Jiang, Li and Wang, Liwei and Zhao, Hengshuang and Liu, Shu and Qi, Xiaojuan and Jia, Jiaya},
  booktitle={CVPR},
  year={2022}
}

@inproceedings{liu2022prototype,
  title={Prototype-Voxel Contrastive Learning for LiDAR Point Cloud Panoptic Segmentation},
  author={Liu, Minzhe and Zhou, Qiang and Zhao, Hengshuang and Li, Jianing and Du, Yuan and Keutzer, Kurt and Du, Li and Zhang, Shanghang},
  booktitle={ICRA},
  year={2022}
}

@article{li2022fully,
  title={Fully convolutional networks for panoptic segmentation with point-based supervision},
  author={Li, Yanwei and Zhao, Hengshuang and Qi, Xiaojuan and Chen, Yukang and Qi, Lu and Wang, Liwei and Li, Zeming and Sun, Jian and Jia, Jiaya},
  journal={TPAMI},
  year={2022}
}

@article{qi2022open,
  title={Open World Entity Segmentation},
  author={Qi, Lu and Kuen, Jason and Wang, Yi and Gu, Jiuxiang and Zhao, Hengshuang and Torr, Philip and Lin, Zhe and Jia, Jiaya},
  journal={TPAMI},
  year={2022}
}

@article{tian2022adaptive,
  title={Adaptive Perspective Distillation for Semantic Segmentation},
  author={Tian, Zhuotao and Chen, Pengguang and Lai, Xin and Jiang, Li and Liu, Shu and Zhao, Hengshuang and Yu, Bei and Yang, Ming-Chang and Jia, Jiaya},
  journal={TPAMI},
  year={2022}
}

@article{sun2022patch,
  title={Patch-based Separable Transformer for Visual Recognition},
  author={Sun, Shuyang and Yue, Xiaoyu and Zhao, Hengshuang and Torr, Philip HS and Bai, Song},
  journal={TPAMI},
  year={2022}
}

@inproceedings{wang2021do,
  title={Do Different Tracking Tasks Require Different Appearance Models?},
  author={Wang, Zhongdao and Zhao, Hengshuang and Li, Yali and Wang, Shengjin and Torr, Philip and Bertinetto, Luca},
  booktitle={NeurIPS},
  year={2021}
}

@inproceedings{yang2021hierarchical,
  title={Hierarchical Interaction Network for Video Object Segmentation from Referring Expressions},
  author={Yang, Zhao and Tang, Yansong and Bertinetto, Luca and Zhao, Hengshuang and Torr, Philip},
  booktitle={BMVC},
  year={2021}
}

@inproceedings{zhao2021point,
  title={Point Transformer},
  author={Zhao, Hengshuang and Jiang, Li and Jia, Jiaya and Torr, Philip and Koltun, Vladlen},
  booktitle={ICCV},
  year={2021}
}

@inproceedings{xu2021dynamic,
  title={Dynamic Divide-and-Conquer Adversarial Training for Robust Semantic Segmentation},
  author={Xu, Xiaogang and Zhao, Hengshuang and Jia, Jiaya},
  booktitle={ICCV},
  year={2021}
}

@inproceedings{hu2021bidirectional,
  title={Bidirectional Projection Network for Cross Dimension Scene Understanding},
  author={Hu, Wenbo and Zhao, Hengshuang and Jiang, Li and Jia, Jiaya and Wong, Tien-Tsin},
  booktitle={CVPR},
  year={2021}
}

@inproceedings{li2021fully,
  title={Fully Convolutional Networks for Panoptic Segmentation},
  author={Li, Yanwei and Zhao, Hengshuang and Qi, Xiaojuan and Wang, Liwei and Li, Zeming and Sun, Jian and Jia, Jiaya},
  booktitle={CVPR},
  year={2021}
}

@inproceedings{chen2021distilling,
  title={Distilling Knowledge via Knowledge Review},
  author={Chen, Pengguang and Liu, Shu and Zhao, Hengshuang and Jia, Jiaya},
  booktitle={CVPR},
  year={2021}
}

@inproceedings{xu2021paconv,
  title={PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds},
  author={Xu, Mutian and Ding, Runyu and Zhao, Hengshuang and Qi, Xiaojuan},
  booktitle={CVPR},
  year={2021}
}

@inproceedings{zheng2021rethinking,
  title={Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers},
  author={Zheng, Sixiao and Lu, Jiachen and Zhao, Hengshuang and Zhu, Xiatian and Luo, Zekun and Wang, Yabiao and Fu, Yanwei and Feng, Jianfeng and Xiang, Tao and Torr, Philip and Zhang, Li},
  booktitle={CVPR},
  year={2021}
}

@inproceedings{lai2021semi,
  title={Semi-supervised Semantic Segmentation with Directional Context-aware Consistency},
  author={Lai, Xin and Tian, Zhuotao and Jiang, Li and Liu, Shu and Zhao, Hengshuang and Wang, Liwei and Jia, Jiaya},
  booktitle={CVPR},
  year={2021}
}

@inproceedings{yu2021dual,
  title={Dual-cross central difference network for face anti-spoofing},
  author={Yu, Zitong and Qin, Yunxiao and Zhao, Hengshuang and Li, Xiaobai and Zhao, Guoying},
  booktitle={IJCAI},
  year={2021}
}

@inproceedings{zhao2020exploring,
  title={Exploring Self-attention for Image Recognition},
  author={Zhao, Hengshuang and Jia, Jiaya and Koltun, Vladlen},
  booktitle={CVPR},
  year={2020}
}

@inproceedings{jiang2020pointgroup,
  title={PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation},
  author={Jiang, Li and Zhao, Hengshuang and Shi, Shaoshuai and Liu, Shu and Fu, Chi-Wing and Jia, Jiaya},
  booktitle={CVPR},
  year={2020}
}

@article{tian2020prior,
  title={Prior Guided Feature Enrichment Network for Few-Shot Segmentation},
  author={Tian, Zhuotao and Zhao, Hengshuang and Shu, Michelle and Yang, Zhicheng and Li, Ruiyu and Jia, Jiaya},
  journal={TPAMI},
  year={2020}
}

@inproceedings{jiang2019hierarchical,
  title={Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentation},
  author={Jiang, Li and Zhao, Hengshuang and Liu, Shu and Shen, Xiaoyong and Fu, Chi-Wing and Jia, Jiaya},
  booktitle={ICCV},
  year={2019}
}

@inproceedings{zhao2019pointweb,
  title={{PointWeb}: Enhancing Local Neighborhood Features for Point Cloud Processing},
  author={Zhao, Hengshuang and Jiang, Li and Fu, Chi-Wing and Jia, Jiaya},
  booktitle={CVPR},
  year={2019}
}

@inproceedings{xiong2019upsnet,
  title={{UPSNet}: A Unified Panoptic Segmentation Network},
  author={Xiong, Yuwen and Liao, Renjie and Zhao, Hengshuang and Hu, Rui and Bai, Min and Yumer, Ersin and Urtasun, Raquel},
  booktitle={CVPR},
  year={2019}
}

@inproceedings{zhao2018psanet,
  title={{PSANet}: Point-wise Spatial Attention Network for Scene Parsing},
  author={Zhao, Hengshuang and Zhang, Yi and Liu, Shu and Shi, Jianping and Loy, Chen Change and Lin, Dahua and Jia, Jiaya},
  booktitle={ECCV},
  year={2018}
}

@inproceedings{zhao2018compositing,
  title={Compositing-aware Image Search},
  author={Zhao, Hengshuang and Shen, Xiaohui and Lin, Zhe and Sunkavalli, Kalyan and Price, Brian and Jia, Jiaya},
  booktitle={ECCV},
  year={2018}
}

@inproceedings{yang2018segstereo,
  title={{SegStereo}: Exploiting Semantic Information for Disparity Estimation},
  author={Yang, Guorun and Zhao, Hengshuang and Shi, Jianping and Deng, Zhidong and Jia, Jiaya},
  booktitle={ECCV},
  year={2018}
}

@inproceedings{zhao2018icnet,
  title={{ICNet} for Real-Time Semantic Segmentation on High-Resolution Images},
  author={Zhao, Hengshuang and Qi, Xiaojuan and Shen, Xiaoyong and Shi, Jianping and Jia, Jiaya},
  booktitle={ECCV},
  year={2018}
}

@inproceedings{zhao2017pyramid,
  title={Pyramid Scene Parsing Network},
  author={Zhao, Hengshuang and Shi, Jianping and Qi, Xiaojuan and Wang, Xiaogang and Jia, Jiaya},
  booktitle={CVPR},
  year={2017}
}

@inproceedings{qi2016augmented,
  title={Augmented Feedback in Semantic Segmentation under Image Level Supervision},
  author={Qi, Xiaojuan and Liu, Zhengzhe and Shi, Jianping and Zhao, Hengshuang and Jia, Jiaya},
  booktitle={ECCV},
  year={2016}
}