Qi Dai

Principal Researcher

Publications

View by:

- RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources
  
  Yijia Fan, Zonglin Di, Zimo Wen, Yifan Yang, Mingxi Cheng, Qi Dai, Bei Liu, Kai Qiu, Yue Dong, Ji Li, Chong Luo
  
  July 2026
  
  arXiv | July 2026
  
  Publication
- Adaptive Inference-Time Scaling via Early-Step Latent Verification for Image Editing
  
  Yue Yu, Yang Jiao, Jiayu Wang, Qiangqiang Dai, Jingjing Chen, Qi Dai
  
  June 2026
  
  arXiv | June 2026
  
  Publication
- Toward Generalist Autonomous Research via Hypothesis-Tree Refinement
  
  Jiajie Jin, Yuyang Hu, Kai Qiu, Qi Dai, Chong Luo, Guanting Dong, Xiaoxian Li, Tong Zhao, Xiaolong Ma, Gongrui Zhang, Zhirong Wu, Bei Liu, Zhengyuan Yang, Linjie Li, Lijuan Wang, Hongjin Qian, Yutao Zhu, Zhicheng Dou
  
  June 2026
  
  arXiv | June 2026
  
  Publication
- Decomposed On-Policy Distillation for Vision-Language Reasoning: Steering Gradients for Visual Grounding
  
  Hee Suk Yoon, Eunseop Yoon, Jaehyun Jang, Soohwan Eom, Jiajing Hong, M. Hasegawa-Johnson, Qi Dai, Chong Luo, C. Yoo
  
  ICML 2026 | May 2026
  
  Publication
- From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills
  
  Zisu Huang, Jingwen Xu, Yifan Yang, Ziyang Gong, Qihao Yang, Muzhao Tian, Xiaohua Wang, Changze Lv, Xuemei Gao, Qi Dai, Bei Liu, Kai Qiu, Xue-Ting Yang, Dongdong Chen, Xiaoqing Zheng, Chong Luo
  
  May 2026
  
  arXiv | May 2026
  
  Publication
- SkillOpt: Executive Strategy for Self-Evolving Agent Skills
  
  Yifan Yang, Ziyang Gong, Weiquan Huang, Qihao Yang, Ziwei Zhou, Zisu Huang, Yan Li, Xuemei Gao, Qi Dai, Bei Liu, Kai Qiu, Yuqing Yang, Dongdong Chen, Xue-Ting Yang, Chong Luo
  
  May 2026
  
  arXiv | May 2026
  
  Publication
- PDCR: Perception-Decomposed Confidence Reward for Vision-Language Reasoning
  
  Heegeon Yoon, Eunseop Yoon, Jinqiu Hong, Soo-Hwan Eom, Gwanhyeong Koo, M. Hasegawa-Johnson, Qi Dai, Chong Luo, C. D. Yoo
  
  CVPR 2026 | May 2026
  
  Publication
- Covering Human Action Space for Computer Use: Data Synthesis and Benchmark
  
  Miaosen Zhang, Xiaohan Zhao, Zhihong Tan, Huoshen Zhou, Yijia Fan, Yifan Yang, Kai Qiu, Bei Liu, Justin Wagle, Chenzhong Yin, Mingxi Cheng, Ji Li, Qi Dai, Chong Luo, Xu Yang, Xin Geng, Baining Guo
  
  May 2026
  
  arXiv | May 2026
  
  Publication
- A Comprehensive Ecosystem for Open-Domain Customized Video Generation
  
  Jingxu Zhang, Yuqian Hong, Daneul Kim, Kai Qiu, Qi Dai, Jianmin Bao, Yifan Yang, Xiaoyan Sun, Chong Luo
  
  ICASSP 2026 | May 2026
  
  DOI
- AVGen-Bench: A Task-Driven Benchmark for Multi-Granular Evaluation of Text-to-Audio-Video Generation
  
  Ziwei Zhou, Zeyuan Lai, Rui Wang, Yifan Yang, Zhening Xing, Yuqing Yang, Qi Dai, Lili Qiu, Chong Luo
  
  April 2026
  
  arXiv | April 2026
  
  Publication
- DynaVid: Learning to Generate Highly Dynamic Videos using Synthetic Motion Data
  
  Wonjoon Jin, J. Won, Janghyeok Han, Qi Dai, Chong Luo, Seung-Hwan Baek, Sunghyun Cho
  
  April 2026
  
  arXiv | April 2026
  
  Publication
- Towards On-Policy SFT: Distribution Discriminant Theory and its Applications in LLM Training
  
  Miaosen Zhang, Yishan Liu, Shuxia Lin, Xu Yang, Qi Dai, Chong Luo, Wei Jiang, Peng-Fei Hou, Anxiang Zeng, Xin Geng, Baining Guo
  
  ICML 2026 | March 2026
  
  Preprint
- RE-TRAC: REcursive TRAjectory Compression for Deep Search Agents
  
  Jialiang Zhu, Gongrui Zhang, Xiaolong Ma, Lin Xu, Miaosen Zhang, Ruiqi Yang, Song Wang, Kai Qiu, Zhirong Wu, Qi Dai, Rui Ma, Bei Liu, Yifan Yang, Chong Luo, Zhengyuan Yang, Linjie Li, Lijuan Wang, Weizhu Chen, Xin Geng, Baining Guo
  
  ICML 2026 | February 2026
  
  Publication
- FlashPortrait: 6x Faster Infinite Portrait Animation with Adaptive Latent Prediction
  
  Shuyuan Tu, Yueming Pan, Yinming Huang, Xintong Han, Zhen Xing, Qi Dai, Kai Qiu, Chong Luo, Zuxuan Wu
  
  December 2025
  
  arXiv | December 2025
  
  Publication
- Video-in-the-Loop: Span-Grounded Long Video QA with Interleaved Reasoning
  
  Chendong Wang, Donglin Bai, Yifan Yang, Xiao Jin, Anlan Zhang, Rui Wang, Shiqi Jiang, Yuqing Yang, Hao Wu, Qi Dai, Chong Luo, Ting Cao, Lili Qiu, Suman Banerjee
  
  ICML 2026 | October 2025
  
  Publication
- Phi-Ground Tech Report: Advancing Perception in GUI Grounding
  
  Miaosen Zhang, Ziqiang Xu, Jialiang Zhu, Qi Dai, Kai Qiu, Yifan Yang, Chong Luo, Tianyi Chen, Justin Wagle, Tim Franklin, Baining Guo
  
  MSR-TR-2025-63 | July 2025
  
  Published by Microsoft
  
  Publication Access
- REDUCIO! Generating 1024⨉1024 Video within 16 Seconds using Extremely Compressed Motion Latents
  
  Rui Tian, Qi Dai, Jianmin Bao, Kai Qiu, Yifan Yang, Chong Luo, Zuxuan Wu, Yu-Gang Jiang
  
  November 2024
  
  ArXiv | November 2024
  
  DOI Github
- LLM2CLIP: Powerful Language Model Unlocks Richer Cross-Modality Representation
  
  Weiquan Huang, Aoqi Wu, Yifan Yang, Xufang Luo, Yuqing Yang, Liang Hu, Qi Dai, Chunyu Wang, Xiyang Dai, Dongdong Chen, Chong Luo, Lili Qiu
  
  November 2024
  
  arXiv | November 2024
  
  DOI Publication
- LLM2CLIP: Powerful Language Model Unlocks Richer Visual Representation
  
  Weiquan Huang, Aoqi Wu, Yifan Yang, Xufang Luo, Yuqing Yang, Liang Hu, Qi Dai, Xiyang Dai, Dongdong Chen, Chong Luo, Lili Qiu
  
  November 2024
  
  arXiv | November 2024
  
  Publication Github Project
- Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions
  
  Minghan Li, Heng Li, Zhi-Qi Cheng, Yifei Dong, Yuxuan Zhou, Jun-Yan He, Qi Dai, Teruko Mitamura, Alexander G. Hauptmann
  
  NeurIPS 2024 | June 2024
  
  DOI Publication Publication
- Aligning Vision Models with Human Aesthetics in Retrieval: Benchmarks and Algorithms
  
  Miaosen Zhang, Yixuan Wei, Zhen Xing, Yifei Ma, Zuxuan Wu, Ji Li, Zheng Zhang, Qi Dai, Chong Luo, Xin Geng, Baining Guo
  
  NeurIPS 2024 | June 2024
  
  DOI Publication Publication
- BlockGCN: Redefine Topology Awareness for Skeleton-Based Action Recognition
  
  Yuxuan Zhou, Xudong Yan, Zhi-Qi Cheng, Yan Yan, Qi Dai, Xian-Sheng Hua
  
  The IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR) | May 2024
  
  Publication
- MicroCinema: A Divide-and-Conquer Approach for Text-to-Video Generation
  
  Yanhui Wang, Jianmin Bao, Wenming Weng, Ruoyu Feng, Dacheng Yin, Tao Yang, Jingxu Zhang, Qi Dai, Chunyu Wang, Kai Qiu, Yuhui Yuan, Xiaoyan Sun, Chong Luo, Baining Guo
  
  CVPR 2024 | November 2023
  
  DOI Publication Publication
- MotionEditor: Editing Video Motion via Content-Aware Diffusion
  
  Shuyuan Tu, Qi Dai, Zhi-Qi Cheng, Hang-Rui Hu, Xintong Han, Zuxuan Wu, Yu-Gang Jiang
  
  CVPR 2024 | November 2023
  
  DOI Publication Publication
- SimDA: Simple Diffusion Adapter for Efficient Video Generation
  
  Zhen Xing, Qi Dai, Han Hu, Zuxuan Wu, Yu-Gang Jiang
  
  CVPR 2024 | August 2023
  
  DOI Publication Publication Publication
- MPII: Multi-Level Mutual Promotion for Inference and Interpretation
  
  Yan Liu, Sanyuan Chen, Yazheng Yang, Qi Dai
  
  ACL 2022 | May 2022
  
  Publication
- Rethinking Spatial Invariance of Convolutional Networks for Object Counting
  
  Zhi-Qi Cheng, Qi Dai, Hong Li, JingKuan Song, Xiao Wu, Alexander Hauptmann
  
  CVPR 2022 | May 2022
  
  Publication
- SimMIM: A Simple Framework for Masked Image Modeling
  
  Zhenda Xie, Zheng Zhang, Yue Cao, Yutong Lin, Jianmin Bao, Zhuliang Yao, Qi Dai, Han Hu
  
  CVPR 2022 | May 2022
  
  Publication
- On the Connection between Local Attention and Dynamic Depth-wise Convolution
  
  Qi Han, Zejia Fan, Qi Dai, Lei Sun, Ming-Ming Cheng, Jiaying Liu, Jingdong Wang
  
  ICLR 2022 | April 2022
  
  Publication
- Temporal Action Detection with Multi-level Supervision
  
  Baifeng Shi, Qi Dai, Judy Hoffman, Kate Saenko, Trevor Darrell, Huijuan Xu
  
  ICCV 2021 | October 2021
  
  Publication
- Informative Dropout for Robust Representation Learning: A Shape-bias Perspective
  
  Baifeng Shi, Dinghuai Zhang, Qi Dai, Zhanxing Zhu, Yadong Mu, Jingdong Wang
  
  ICML 2020 | July 2020
  
  Publication
- Weakly-Supervised Action Localization by Generative Attention Modeling
  
  Baifeng Shi, Qi Dai, Yadong Mu, Jingdong Wang
  
  CVPR 2020 | June 2020
  
  Publication PDF
- Learning spatial awareness to improve crowd counting
  
  Zhi-Qi Cheng, Jun-Xiu Li, Qi Dai, Xiao Wu, Alexander G Hauptmann
  
  ICCV | October 2019
  
  Publication
- Improving the Learning of Multi-column Convolutional Neural Network for Crowd Counting
  
  Zhi-Qi Cheng, Jun-Xiu Li, Qi Dai, Xiao Wu, Jun-Yan He, Alexander G Hauptmann
  
  ACM Multimedia | October 2019
  
  Publication
- Decoupling Localization and Classification in Single Shot Temporal Action Detection
  
  Yupan Huang, Qi Dai, Yutong Lu
  
  ICME | July 2019
  
  Publication
- Deep Incremental Hashing Network for Efficient Image Retrieval
  
  Dayan Wu, Qi Dai, Jing Liu, Bo Li, Weiping Wang
  
  CVPR | June 2019
  
  Publication
- Recurrent tubelet proposal and recognition networks for action detection
  
  Dong Li, Zhaofan Qiu, Qi Dai, Ting Yao, Tao Mei
  
  ECCV | September 2018
  
  Publication
- Deep domain adaptation hashing with adversarial learning
  
  Fuchen Long, Ting Yao, Qi Dai, Xinmei Tian, Jiebo Luo, Tao Mei
  
  SIGIR | July 2018
  
  Publication

- RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources
  
  Yijia Fan, Zonglin Di, Zimo Wen, Yifan Yang, Mingxi Cheng, Qi Dai, Bei Liu, Kai Qiu, Yue Dong, Ji Li, Chong Luo
  
  July 2026
  
  arXiv | July 2026
  
  Publication
- Adaptive Inference-Time Scaling via Early-Step Latent Verification for Image Editing
  
  Yue Yu, Yang Jiao, Jiayu Wang, Qiangqiang Dai, Jingjing Chen, Qi Dai
  
  June 2026
  
  arXiv | June 2026
  
  Publication
- Toward Generalist Autonomous Research via Hypothesis-Tree Refinement
  
  Jiajie Jin, Yuyang Hu, Kai Qiu, Qi Dai, Chong Luo, Guanting Dong, Xiaoxian Li, Tong Zhao, Xiaolong Ma, Gongrui Zhang, Zhirong Wu, Bei Liu, Zhengyuan Yang, Linjie Li, Lijuan Wang, Hongjin Qian, Yutao Zhu, Zhicheng Dou
  
  June 2026
  
  arXiv | June 2026
  
  Publication
- SkillOpt: Executive Strategy for Self-Evolving Agent Skills
  
  Yifan Yang, Ziyang Gong, Weiquan Huang, Qihao Yang, Ziwei Zhou, Zisu Huang, Yan Li, Xuemei Gao, Qi Dai, Bei Liu, Kai Qiu, Yuqing Yang, Dongdong Chen, Xue-Ting Yang, Chong Luo
  
  May 2026
  
  arXiv | May 2026
  
  Publication
- From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills
  
  Zisu Huang, Jingwen Xu, Yifan Yang, Ziyang Gong, Qihao Yang, Muzhao Tian, Xiaohua Wang, Changze Lv, Xuemei Gao, Qi Dai, Bei Liu, Kai Qiu, Xue-Ting Yang, Dongdong Chen, Xiaoqing Zheng, Chong Luo
  
  May 2026
  
  arXiv | May 2026
  
  Publication
- Covering Human Action Space for Computer Use: Data Synthesis and Benchmark
  
  Miaosen Zhang, Xiaohan Zhao, Zhihong Tan, Huoshen Zhou, Yijia Fan, Yifan Yang, Kai Qiu, Bei Liu, Justin Wagle, Chenzhong Yin, Mingxi Cheng, Ji Li, Qi Dai, Chong Luo, Xu Yang, Xin Geng, Baining Guo
  
  May 2026
  
  arXiv | May 2026
  
  Publication
- Towards On-Policy SFT: Distribution Discriminant Theory and its Applications in LLM Training
  
  Miaosen Zhang, Yishan Liu, Shuxia Lin, Xu Yang, Qi Dai, Chong Luo, Wei Jiang, Peng-Fei Hou, Anxiang Zeng, Xin Geng, Baining Guo
  
  ICML 2026 | March 2026
  
  Preprint
- RE-TRAC: REcursive TRAjectory Compression for Deep Search Agents
  
  Jialiang Zhu, Gongrui Zhang, Xiaolong Ma, Lin Xu, Miaosen Zhang, Ruiqi Yang, Song Wang, Kai Qiu, Zhirong Wu, Qi Dai, Rui Ma, Bei Liu, Yifan Yang, Chong Luo, Zhengyuan Yang, Linjie Li, Lijuan Wang, Weizhu Chen, Xin Geng, Baining Guo
  
  ICML 2026 | February 2026
  
  Publication
- Video-in-the-Loop: Span-Grounded Long Video QA with Interleaved Reasoning
  
  Chendong Wang, Donglin Bai, Yifan Yang, Xiao Jin, Anlan Zhang, Rui Wang, Shiqi Jiang, Yuqing Yang, Hao Wu, Qi Dai, Chong Luo, Ting Cao, Lili Qiu, Suman Banerjee
  
  ICML 2026 | October 2025
  
  Publication
- Phi-Ground Tech Report: Advancing Perception in GUI Grounding
  
  Miaosen Zhang, Ziqiang Xu, Jialiang Zhu, Qi Dai, Kai Qiu, Yifan Yang, Chong Luo, Tianyi Chen, Justin Wagle, Tim Franklin, Baining Guo
  
  MSR-TR-2025-63 | July 2025
  
  Published by Microsoft
  
  Publication Access
- Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions
  
  Minghan Li, Heng Li, Zhi-Qi Cheng, Yifei Dong, Yuxuan Zhou, Jun-Yan He, Qi Dai, Teruko Mitamura, Alexander G. Hauptmann
  
  NeurIPS 2024 | June 2024
  
  DOI Publication Publication
- Aligning Vision Models with Human Aesthetics in Retrieval: Benchmarks and Algorithms
  
  Miaosen Zhang, Yixuan Wei, Zhen Xing, Yifei Ma, Zuxuan Wu, Ji Li, Zheng Zhang, Qi Dai, Chong Luo, Xin Geng, Baining Guo
  
  NeurIPS 2024 | June 2024
  
  DOI Publication Publication
- On the Connection between Local Attention and Dynamic Depth-wise Convolution
  
  Qi Han, Zejia Fan, Qi Dai, Lei Sun, Ming-Ming Cheng, Jiaying Liu, Jingdong Wang
  
  ICLR 2022 | April 2022
  
  Publication
- Informative Dropout for Robust Representation Learning: A Shape-bias Perspective
  
  Baifeng Shi, Dinghuai Zhang, Qi Dai, Zhanxing Zhu, Yadong Mu, Jingdong Wang
  
  ICML 2020 | July 2020
  
  Publication
- RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources
  
  Yijia Fan, Zonglin Di, Zimo Wen, Yifan Yang, Mingxi Cheng, Qi Dai, Bei Liu, Kai Qiu, Yue Dong, Ji Li, Chong Luo
  
  July 2026
  
  arXiv | July 2026
  
  Publication
- Adaptive Inference-Time Scaling via Early-Step Latent Verification for Image Editing
  
  Yue Yu, Yang Jiao, Jiayu Wang, Qiangqiang Dai, Jingjing Chen, Qi Dai
  
  June 2026
  
  arXiv | June 2026
  
  Publication
- Decomposed On-Policy Distillation for Vision-Language Reasoning: Steering Gradients for Visual Grounding
  
  Hee Suk Yoon, Eunseop Yoon, Jaehyun Jang, Soohwan Eom, Jiajing Hong, M. Hasegawa-Johnson, Qi Dai, Chong Luo, C. Yoo
  
  ICML 2026 | May 2026
  
  Publication
- PDCR: Perception-Decomposed Confidence Reward for Vision-Language Reasoning
  
  Heegeon Yoon, Eunseop Yoon, Jinqiu Hong, Soo-Hwan Eom, Gwanhyeong Koo, M. Hasegawa-Johnson, Qi Dai, Chong Luo, C. D. Yoo
  
  CVPR 2026 | May 2026
  
  Publication
- AVGen-Bench: A Task-Driven Benchmark for Multi-Granular Evaluation of Text-to-Audio-Video Generation
  
  Ziwei Zhou, Zeyuan Lai, Rui Wang, Yifan Yang, Zhening Xing, Yuqing Yang, Qi Dai, Lili Qiu, Chong Luo
  
  April 2026
  
  arXiv | April 2026
  
  Publication
- DynaVid: Learning to Generate Highly Dynamic Videos using Synthetic Motion Data
  
  Wonjoon Jin, J. Won, Janghyeok Han, Qi Dai, Chong Luo, Seung-Hwan Baek, Sunghyun Cho
  
  April 2026
  
  arXiv | April 2026
  
  Publication
- Towards On-Policy SFT: Distribution Discriminant Theory and its Applications in LLM Training
  
  Miaosen Zhang, Yishan Liu, Shuxia Lin, Xu Yang, Qi Dai, Chong Luo, Wei Jiang, Peng-Fei Hou, Anxiang Zeng, Xin Geng, Baining Guo
  
  ICML 2026 | March 2026
  
  Preprint
- FlashPortrait: 6x Faster Infinite Portrait Animation with Adaptive Latent Prediction
  
  Shuyuan Tu, Yueming Pan, Yinming Huang, Xintong Han, Zhen Xing, Qi Dai, Kai Qiu, Chong Luo, Zuxuan Wu
  
  December 2025
  
  arXiv | December 2025
  
  Publication
- Video-in-the-Loop: Span-Grounded Long Video QA with Interleaved Reasoning
  
  Chendong Wang, Donglin Bai, Yifan Yang, Xiao Jin, Anlan Zhang, Rui Wang, Shiqi Jiang, Yuqing Yang, Hao Wu, Qi Dai, Chong Luo, Ting Cao, Lili Qiu, Suman Banerjee
  
  ICML 2026 | October 2025
  
  Publication
- Phi-Ground Tech Report: Advancing Perception in GUI Grounding
  
  Miaosen Zhang, Ziqiang Xu, Jialiang Zhu, Qi Dai, Kai Qiu, Yifan Yang, Chong Luo, Tianyi Chen, Justin Wagle, Tim Franklin, Baining Guo
  
  MSR-TR-2025-63 | July 2025
  
  Published by Microsoft
  
  Publication Access
- REDUCIO! Generating 1024⨉1024 Video within 16 Seconds using Extremely Compressed Motion Latents
  
  Rui Tian, Qi Dai, Jianmin Bao, Kai Qiu, Yifan Yang, Chong Luo, Zuxuan Wu, Yu-Gang Jiang
  
  November 2024
  
  ArXiv | November 2024
  
  DOI Github
- LLM2CLIP: Powerful Language Model Unlocks Richer Cross-Modality Representation
  
  Weiquan Huang, Aoqi Wu, Yifan Yang, Xufang Luo, Yuqing Yang, Liang Hu, Qi Dai, Chunyu Wang, Xiyang Dai, Dongdong Chen, Chong Luo, Lili Qiu
  
  November 2024
  
  arXiv | November 2024
  
  DOI Publication
- LLM2CLIP: Powerful Language Model Unlocks Richer Visual Representation
  
  Weiquan Huang, Aoqi Wu, Yifan Yang, Xufang Luo, Yuqing Yang, Liang Hu, Qi Dai, Xiyang Dai, Dongdong Chen, Chong Luo, Lili Qiu
  
  November 2024
  
  arXiv | November 2024
  
  Publication Github Project
- Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions
  
  Minghan Li, Heng Li, Zhi-Qi Cheng, Yifei Dong, Yuxuan Zhou, Jun-Yan He, Qi Dai, Teruko Mitamura, Alexander G. Hauptmann
  
  NeurIPS 2024 | June 2024
  
  DOI Publication Publication
- BlockGCN: Redefine Topology Awareness for Skeleton-Based Action Recognition
  
  Yuxuan Zhou, Xudong Yan, Zhi-Qi Cheng, Yan Yan, Qi Dai, Xian-Sheng Hua
  
  The IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR) | May 2024
  
  Publication
- MotionEditor: Editing Video Motion via Content-Aware Diffusion
  
  Shuyuan Tu, Qi Dai, Zhi-Qi Cheng, Hang-Rui Hu, Xintong Han, Zuxuan Wu, Yu-Gang Jiang
  
  CVPR 2024 | November 2023
  
  DOI Publication Publication
- MicroCinema: A Divide-and-Conquer Approach for Text-to-Video Generation
  
  Yanhui Wang, Jianmin Bao, Wenming Weng, Ruoyu Feng, Dacheng Yin, Tao Yang, Jingxu Zhang, Qi Dai, Chunyu Wang, Kai Qiu, Yuhui Yuan, Xiaoyan Sun, Chong Luo, Baining Guo
  
  CVPR 2024 | November 2023
  
  DOI Publication Publication
- SimDA: Simple Diffusion Adapter for Efficient Video Generation
  
  Zhen Xing, Qi Dai, Han Hu, Zuxuan Wu, Yu-Gang Jiang
  
  CVPR 2024 | August 2023
  
  DOI Publication Publication Publication
- SimMIM: A Simple Framework for Masked Image Modeling
  
  Zhenda Xie, Zheng Zhang, Yue Cao, Yutong Lin, Jianmin Bao, Zhuliang Yao, Qi Dai, Han Hu
  
  CVPR 2022 | May 2022
  
  Publication
- Rethinking Spatial Invariance of Convolutional Networks for Object Counting
  
  Zhi-Qi Cheng, Qi Dai, Hong Li, JingKuan Song, Xiao Wu, Alexander Hauptmann
  
  CVPR 2022 | May 2022
  
  Publication
- Temporal Action Detection with Multi-level Supervision
  
  Baifeng Shi, Qi Dai, Judy Hoffman, Kate Saenko, Trevor Darrell, Huijuan Xu
  
  ICCV 2021 | October 2021
  
  Publication
- Weakly-Supervised Action Localization by Generative Attention Modeling
  
  Baifeng Shi, Qi Dai, Yadong Mu, Jingdong Wang
  
  CVPR 2020 | June 2020
  
  Publication PDF
- Learning spatial awareness to improve crowd counting
  
  Zhi-Qi Cheng, Jun-Xiu Li, Qi Dai, Xiao Wu, Alexander G Hauptmann
  
  ICCV | October 2019
  
  Publication
- Improving the Learning of Multi-column Convolutional Neural Network for Crowd Counting
  
  Zhi-Qi Cheng, Jun-Xiu Li, Qi Dai, Xiao Wu, Jun-Yan He, Alexander G Hauptmann
  
  ACM Multimedia | October 2019
  
  Publication
- Decoupling Localization and Classification in Single Shot Temporal Action Detection
  
  Yupan Huang, Qi Dai, Yutong Lu
  
  ICME | July 2019
  
  Publication
- Deep Incremental Hashing Network for Efficient Image Retrieval
  
  Dayan Wu, Qi Dai, Jing Liu, Bo Li, Weiping Wang
  
  CVPR | June 2019
  
  Publication
- Recurrent tubelet proposal and recognition networks for action detection
  
  Dong Li, Zhaofan Qiu, Qi Dai, Ting Yao, Tao Mei
  
  ECCV | September 2018
  
  Publication
- Deep domain adaptation hashing with adversarial learning
  
  Fuchen Long, Ting Yao, Qi Dai, Xinmei Tian, Jiebo Luo, Tao Mei
  
  SIGIR | July 2018
  
  Publication
- Covering Human Action Space for Computer Use: Data Synthesis and Benchmark
  
  Miaosen Zhang, Xiaohan Zhao, Zhihong Tan, Huoshen Zhou, Yijia Fan, Yifan Yang, Kai Qiu, Bei Liu, Justin Wagle, Chenzhong Yin, Mingxi Cheng, Ji Li, Qi Dai, Chong Luo, Xu Yang, Xin Geng, Baining Guo
  
  May 2026
  
  arXiv | May 2026
  
  Publication
- A Comprehensive Ecosystem for Open-Domain Customized Video Generation
  
  Jingxu Zhang, Yuqian Hong, Daneul Kim, Kai Qiu, Qi Dai, Jianmin Bao, Yifan Yang, Xiaoyan Sun, Chong Luo
  
  ICASSP 2026 | May 2026
  
  DOI
- MPII: Multi-Level Mutual Promotion for Inference and Interpretation
  
  Yan Liu, Sanyuan Chen, Yazheng Yang, Qi Dai
  
  ACL 2022 | May 2022
  
  Publication

- RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources
  
  Yijia Fan, Zonglin Di, Zimo Wen, Yifan Yang, Mingxi Cheng, Qi Dai, Bei Liu, Kai Qiu, Yue Dong, Ji Li, Chong Luo
  
  July 2026
  
  arXiv | July 2026
  
  Publication
- Adaptive Inference-Time Scaling via Early-Step Latent Verification for Image Editing
  
  Yue Yu, Yang Jiao, Jiayu Wang, Qiangqiang Dai, Jingjing Chen, Qi Dai
  
  June 2026
  
  arXiv | June 2026
  
  Publication
- Toward Generalist Autonomous Research via Hypothesis-Tree Refinement
  
  Jiajie Jin, Yuyang Hu, Kai Qiu, Qi Dai, Chong Luo, Guanting Dong, Xiaoxian Li, Tong Zhao, Xiaolong Ma, Gongrui Zhang, Zhirong Wu, Bei Liu, Zhengyuan Yang, Linjie Li, Lijuan Wang, Hongjin Qian, Yutao Zhu, Zhicheng Dou
  
  June 2026
  
  arXiv | June 2026
  
  Publication
- SkillOpt: Executive Strategy for Self-Evolving Agent Skills
  
  Yifan Yang, Ziyang Gong, Weiquan Huang, Qihao Yang, Ziwei Zhou, Zisu Huang, Yan Li, Xuemei Gao, Qi Dai, Bei Liu, Kai Qiu, Yuqing Yang, Dongdong Chen, Xue-Ting Yang, Chong Luo
  
  May 2026
  
  arXiv | May 2026
  
  Publication
- From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills
  
  Zisu Huang, Jingwen Xu, Yifan Yang, Ziyang Gong, Qihao Yang, Muzhao Tian, Xiaohua Wang, Changze Lv, Xuemei Gao, Qi Dai, Bei Liu, Kai Qiu, Xue-Ting Yang, Dongdong Chen, Xiaoqing Zheng, Chong Luo
  
  May 2026
  
  arXiv | May 2026
  
  Publication
- Covering Human Action Space for Computer Use: Data Synthesis and Benchmark
  
  Miaosen Zhang, Xiaohan Zhao, Zhihong Tan, Huoshen Zhou, Yijia Fan, Yifan Yang, Kai Qiu, Bei Liu, Justin Wagle, Chenzhong Yin, Mingxi Cheng, Ji Li, Qi Dai, Chong Luo, Xu Yang, Xin Geng, Baining Guo
  
  May 2026
  
  arXiv | May 2026
  
  Publication
- AVGen-Bench: A Task-Driven Benchmark for Multi-Granular Evaluation of Text-to-Audio-Video Generation
  
  Ziwei Zhou, Zeyuan Lai, Rui Wang, Yifan Yang, Zhening Xing, Yuqing Yang, Qi Dai, Lili Qiu, Chong Luo
  
  April 2026
  
  arXiv | April 2026
  
  Publication
- DynaVid: Learning to Generate Highly Dynamic Videos using Synthetic Motion Data
  
  Wonjoon Jin, J. Won, Janghyeok Han, Qi Dai, Chong Luo, Seung-Hwan Baek, Sunghyun Cho
  
  April 2026
  
  arXiv | April 2026
  
  Publication
- FlashPortrait: 6x Faster Infinite Portrait Animation with Adaptive Latent Prediction
  
  Shuyuan Tu, Yueming Pan, Yinming Huang, Xintong Han, Zhen Xing, Qi Dai, Kai Qiu, Chong Luo, Zuxuan Wu
  
  December 2025
  
  arXiv | December 2025
  
  Publication
- REDUCIO! Generating 1024⨉1024 Video within 16 Seconds using Extremely Compressed Motion Latents
  
  Rui Tian, Qi Dai, Jianmin Bao, Kai Qiu, Yifan Yang, Chong Luo, Zuxuan Wu, Yu-Gang Jiang
  
  November 2024
  
  ArXiv | November 2024
  
  DOI Github
- LLM2CLIP: Powerful Language Model Unlocks Richer Cross-Modality Representation
  
  Weiquan Huang, Aoqi Wu, Yifan Yang, Xufang Luo, Yuqing Yang, Liang Hu, Qi Dai, Chunyu Wang, Xiyang Dai, Dongdong Chen, Chong Luo, Lili Qiu
  
  November 2024
  
  arXiv | November 2024
  
  DOI Publication
- LLM2CLIP: Powerful Language Model Unlocks Richer Visual Representation
  
  Weiquan Huang, Aoqi Wu, Yifan Yang, Xufang Luo, Yuqing Yang, Liang Hu, Qi Dai, Xiyang Dai, Dongdong Chen, Chong Luo, Lili Qiu
  
  November 2024
  
  arXiv | November 2024
  
  Publication Github Project
- Decomposed On-Policy Distillation for Vision-Language Reasoning: Steering Gradients for Visual Grounding
  
  Hee Suk Yoon, Eunseop Yoon, Jaehyun Jang, Soohwan Eom, Jiajing Hong, M. Hasegawa-Johnson, Qi Dai, Chong Luo, C. Yoo
  
  ICML 2026 | May 2026
  
  Publication
- PDCR: Perception-Decomposed Confidence Reward for Vision-Language Reasoning
  
  Heegeon Yoon, Eunseop Yoon, Jinqiu Hong, Soo-Hwan Eom, Gwanhyeong Koo, M. Hasegawa-Johnson, Qi Dai, Chong Luo, C. D. Yoo
  
  CVPR 2026 | May 2026
  
  Publication
- A Comprehensive Ecosystem for Open-Domain Customized Video Generation
  
  Jingxu Zhang, Yuqian Hong, Daneul Kim, Kai Qiu, Qi Dai, Jianmin Bao, Yifan Yang, Xiaoyan Sun, Chong Luo
  
  ICASSP 2026 | May 2026
  
  DOI
- Towards On-Policy SFT: Distribution Discriminant Theory and its Applications in LLM Training
  
  Miaosen Zhang, Yishan Liu, Shuxia Lin, Xu Yang, Qi Dai, Chong Luo, Wei Jiang, Peng-Fei Hou, Anxiang Zeng, Xin Geng, Baining Guo
  
  ICML 2026 | March 2026
  
  Preprint
- RE-TRAC: REcursive TRAjectory Compression for Deep Search Agents
  
  Jialiang Zhu, Gongrui Zhang, Xiaolong Ma, Lin Xu, Miaosen Zhang, Ruiqi Yang, Song Wang, Kai Qiu, Zhirong Wu, Qi Dai, Rui Ma, Bei Liu, Yifan Yang, Chong Luo, Zhengyuan Yang, Linjie Li, Lijuan Wang, Weizhu Chen, Xin Geng, Baining Guo
  
  ICML 2026 | February 2026
  
  Publication
- Video-in-the-Loop: Span-Grounded Long Video QA with Interleaved Reasoning
  
  Chendong Wang, Donglin Bai, Yifan Yang, Xiao Jin, Anlan Zhang, Rui Wang, Shiqi Jiang, Yuqing Yang, Hao Wu, Qi Dai, Chong Luo, Ting Cao, Lili Qiu, Suman Banerjee
  
  ICML 2026 | October 2025
  
  Publication
- Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions
  
  Minghan Li, Heng Li, Zhi-Qi Cheng, Yifei Dong, Yuxuan Zhou, Jun-Yan He, Qi Dai, Teruko Mitamura, Alexander G. Hauptmann
  
  NeurIPS 2024 | June 2024
  
  DOI Publication Publication
- Aligning Vision Models with Human Aesthetics in Retrieval: Benchmarks and Algorithms
  
  Miaosen Zhang, Yixuan Wei, Zhen Xing, Yifei Ma, Zuxuan Wu, Ji Li, Zheng Zhang, Qi Dai, Chong Luo, Xin Geng, Baining Guo
  
  NeurIPS 2024 | June 2024
  
  DOI Publication Publication
- BlockGCN: Redefine Topology Awareness for Skeleton-Based Action Recognition
  
  Yuxuan Zhou, Xudong Yan, Zhi-Qi Cheng, Yan Yan, Qi Dai, Xian-Sheng Hua
  
  The IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR) | May 2024
  
  Publication
- MotionEditor: Editing Video Motion via Content-Aware Diffusion
  
  Shuyuan Tu, Qi Dai, Zhi-Qi Cheng, Hang-Rui Hu, Xintong Han, Zuxuan Wu, Yu-Gang Jiang
  
  CVPR 2024 | November 2023
  
  DOI Publication Publication
- MicroCinema: A Divide-and-Conquer Approach for Text-to-Video Generation
  
  Yanhui Wang, Jianmin Bao, Wenming Weng, Ruoyu Feng, Dacheng Yin, Tao Yang, Jingxu Zhang, Qi Dai, Chunyu Wang, Kai Qiu, Yuhui Yuan, Xiaoyan Sun, Chong Luo, Baining Guo
  
  CVPR 2024 | November 2023
  
  DOI Publication Publication
- SimDA: Simple Diffusion Adapter for Efficient Video Generation
  
  Zhen Xing, Qi Dai, Han Hu, Zuxuan Wu, Yu-Gang Jiang
  
  CVPR 2024 | August 2023
  
  DOI Publication Publication Publication
- MPII: Multi-Level Mutual Promotion for Inference and Interpretation
  
  Yan Liu, Sanyuan Chen, Yazheng Yang, Qi Dai
  
  ACL 2022 | May 2022
  
  Publication
- SimMIM: A Simple Framework for Masked Image Modeling
  
  Zhenda Xie, Zheng Zhang, Yue Cao, Yutong Lin, Jianmin Bao, Zhuliang Yao, Qi Dai, Han Hu
  
  CVPR 2022 | May 2022
  
  Publication
- Rethinking Spatial Invariance of Convolutional Networks for Object Counting
  
  Zhi-Qi Cheng, Qi Dai, Hong Li, JingKuan Song, Xiao Wu, Alexander Hauptmann
  
  CVPR 2022 | May 2022
  
  Publication
- On the Connection between Local Attention and Dynamic Depth-wise Convolution
  
  Qi Han, Zejia Fan, Qi Dai, Lei Sun, Ming-Ming Cheng, Jiaying Liu, Jingdong Wang
  
  ICLR 2022 | April 2022
  
  Publication
- Temporal Action Detection with Multi-level Supervision
  
  Baifeng Shi, Qi Dai, Judy Hoffman, Kate Saenko, Trevor Darrell, Huijuan Xu
  
  ICCV 2021 | October 2021
  
  Publication
- Informative Dropout for Robust Representation Learning: A Shape-bias Perspective
  
  Baifeng Shi, Dinghuai Zhang, Qi Dai, Zhanxing Zhu, Yadong Mu, Jingdong Wang
  
  ICML 2020 | July 2020
  
  Publication
- Weakly-Supervised Action Localization by Generative Attention Modeling
  
  Baifeng Shi, Qi Dai, Yadong Mu, Jingdong Wang
  
  CVPR 2020 | June 2020
  
  Publication PDF
- Learning spatial awareness to improve crowd counting
  
  Zhi-Qi Cheng, Jun-Xiu Li, Qi Dai, Xiao Wu, Alexander G Hauptmann
  
  ICCV | October 2019
  
  Publication
- Improving the Learning of Multi-column Convolutional Neural Network for Crowd Counting
  
  Zhi-Qi Cheng, Jun-Xiu Li, Qi Dai, Xiao Wu, Jun-Yan He, Alexander G Hauptmann
  
  ACM Multimedia | October 2019
  
  Publication
- Decoupling Localization and Classification in Single Shot Temporal Action Detection
  
  Yupan Huang, Qi Dai, Yutong Lu
  
  ICME | July 2019
  
  Publication
- Deep Incremental Hashing Network for Efficient Image Retrieval
  
  Dayan Wu, Qi Dai, Jing Liu, Bo Li, Weiping Wang
  
  CVPR | June 2019
  
  Publication
- Recurrent tubelet proposal and recognition networks for action detection
  
  Dong Li, Zhaofan Qiu, Qi Dai, Ting Yao, Tao Mei
  
  ECCV | September 2018
  
  Publication
- Deep domain adaptation hashing with adversarial learning
  
  Fuchen Long, Ting Yao, Qi Dai, Xinmei Tian, Jiebo Luo, Tao Mei
  
  SIGIR | July 2018
  
  Publication
- Phi-Ground Tech Report: Advancing Perception in GUI Grounding
  
  Miaosen Zhang, Ziqiang Xu, Jialiang Zhu, Qi Dai, Kai Qiu, Yifan Yang, Chong Luo, Tianyi Chen, Justin Wagle, Tim Franklin, Baining Guo
  
  MSR-TR-2025-63 | July 2025
  
  Published by Microsoft
  
  Publication Access

Qi Dai

Publications

RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources

Adaptive Inference-Time Scaling via Early-Step Latent Verification for Image Editing

Toward Generalist Autonomous Research via Hypothesis-Tree Refinement

Decomposed On-Policy Distillation for Vision-Language Reasoning: Steering Gradients for Visual Grounding

From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills

SkillOpt: Executive Strategy for Self-Evolving Agent Skills

PDCR: Perception-Decomposed Confidence Reward for Vision-Language Reasoning

Covering Human Action Space for Computer Use: Data Synthesis and Benchmark

A Comprehensive Ecosystem for Open-Domain Customized Video Generation

AVGen-Bench: A Task-Driven Benchmark for Multi-Granular Evaluation of Text-to-Audio-Video Generation

DynaVid: Learning to Generate Highly Dynamic Videos using Synthetic Motion Data

Towards On-Policy SFT: Distribution Discriminant Theory and its Applications in LLM Training

RE-TRAC: REcursive TRAjectory Compression for Deep Search Agents

FlashPortrait: 6x Faster Infinite Portrait Animation with Adaptive Latent Prediction

Video-in-the-Loop: Span-Grounded Long Video QA with Interleaved Reasoning

Phi-Ground Tech Report: Advancing Perception in GUI Grounding

REDUCIO! Generating 1024⨉1024 Video within 16 Seconds using Extremely Compressed Motion Latents

LLM2CLIP: Powerful Language Model Unlocks Richer Cross-Modality Representation

LLM2CLIP: Powerful Language Model Unlocks Richer Visual Representation

Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions

Aligning Vision Models with Human Aesthetics in Retrieval: Benchmarks and Algorithms

BlockGCN: Redefine Topology Awareness for Skeleton-Based Action Recognition

MicroCinema: A Divide-and-Conquer Approach for Text-to-Video Generation

MotionEditor: Editing Video Motion via Content-Aware Diffusion

SimDA: Simple Diffusion Adapter for Efficient Video Generation

MPII: Multi-Level Mutual Promotion for Inference and Interpretation

Rethinking Spatial Invariance of Convolutional Networks for Object Counting

SimMIM: A Simple Framework for Masked Image Modeling

On the Connection between Local Attention and Dynamic Depth-wise Convolution

Temporal Action Detection with Multi-level Supervision

Informative Dropout for Robust Representation Learning: A Shape-bias Perspective

Weakly-Supervised Action Localization by Generative Attention Modeling

Learning spatial awareness to improve crowd counting

Improving the Learning of Multi-column Convolutional Neural Network for Crowd Counting

Decoupling Localization and Classification in Single Shot Temporal Action Detection

Deep Incremental Hashing Network for Efficient Image Retrieval

Recurrent tubelet proposal and recognition networks for action detection

Deep domain adaptation hashing with adversarial learning

RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources

Adaptive Inference-Time Scaling via Early-Step Latent Verification for Image Editing

Toward Generalist Autonomous Research via Hypothesis-Tree Refinement

SkillOpt: Executive Strategy for Self-Evolving Agent Skills

From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills

Covering Human Action Space for Computer Use: Data Synthesis and Benchmark

Towards On-Policy SFT: Distribution Discriminant Theory and its Applications in LLM Training

RE-TRAC: REcursive TRAjectory Compression for Deep Search Agents

Video-in-the-Loop: Span-Grounded Long Video QA with Interleaved Reasoning

Phi-Ground Tech Report: Advancing Perception in GUI Grounding

Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions

Aligning Vision Models with Human Aesthetics in Retrieval: Benchmarks and Algorithms

On the Connection between Local Attention and Dynamic Depth-wise Convolution

Informative Dropout for Robust Representation Learning: A Shape-bias Perspective

RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources

Adaptive Inference-Time Scaling via Early-Step Latent Verification for Image Editing

Decomposed On-Policy Distillation for Vision-Language Reasoning: Steering Gradients for Visual Grounding

PDCR: Perception-Decomposed Confidence Reward for Vision-Language Reasoning

AVGen-Bench: A Task-Driven Benchmark for Multi-Granular Evaluation of Text-to-Audio-Video Generation

DynaVid: Learning to Generate Highly Dynamic Videos using Synthetic Motion Data

Towards On-Policy SFT: Distribution Discriminant Theory and its Applications in LLM Training

FlashPortrait: 6x Faster Infinite Portrait Animation with Adaptive Latent Prediction

Video-in-the-Loop: Span-Grounded Long Video QA with Interleaved Reasoning

Phi-Ground Tech Report: Advancing Perception in GUI Grounding

REDUCIO! Generating 1024⨉1024 Video within 16 Seconds using Extremely Compressed Motion Latents

LLM2CLIP: Powerful Language Model Unlocks Richer Cross-Modality Representation

LLM2CLIP: Powerful Language Model Unlocks Richer Visual Representation

Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions

BlockGCN: Redefine Topology Awareness for Skeleton-Based Action Recognition

MotionEditor: Editing Video Motion via Content-Aware Diffusion

MicroCinema: A Divide-and-Conquer Approach for Text-to-Video Generation

SimDA: Simple Diffusion Adapter for Efficient Video Generation

SimMIM: A Simple Framework for Masked Image Modeling

Rethinking Spatial Invariance of Convolutional Networks for Object Counting

Temporal Action Detection with Multi-level Supervision

Weakly-Supervised Action Localization by Generative Attention Modeling

Learning spatial awareness to improve crowd counting

Improving the Learning of Multi-column Convolutional Neural Network for Crowd Counting

Decoupling Localization and Classification in Single Shot Temporal Action Detection

Deep Incremental Hashing Network for Efficient Image Retrieval