PPaperPicks

Qi Dai

Microsoft Research Asia, Beijing, China

22 papers at tracked venues · 20 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0002-4693-2968 ↗Google Scholar ↗Homepage ↗

Venues

CVPR ×9ICCV ×5AAAI ×3NeurIPS ×2WACV ×2ACL ×1

Frequent coauthors

Shuyuan Tu
DBLP profile ↗ORCID search ↗
×3
Miaosen Zhang
DBLP profile ↗ORCID search ↗
×2
Zhen Xing
DBLP profile ↗ORCID search ↗
×2
Fengyi Wu
DBLP profile ↗ORCID search ↗
×1
Ziqin Zhou
DBLP profile ↗ORCID search ↗
×1
Weiquan Huang
DBLP profile ↗ORCID search ↗
×1
Jiayu Wang
DBLP profile ↗ORCID search ↗
×1
Wonjoon Jin
DBLP profile ↗ORCID search ↗
×1
Ding Ding
DBLP profile ↗ORCID search ↗
×1
Byung-Ki Kwon
DBLP profile ↗ORCID search ↗
×1
Quanhao Li
DBLP profile ↗ORCID search ↗
×1
Rui Tian
DBLP profile ↗ORCID search ↗
×1

Papers

  1. GoViG: Goal-Conditioned Visual Navigation Instruction Generation via Multimodal Reasoning
    ACL 2026 ·
    Fengyi Wu
    DBLP profile ↗ORCID search ↗
  2. HiTVideo: Hierarchical Tokenizers for Enhancing Text-to-Video Generation with Autoregressive Large Language Models
    AAAI 2026 ·
    Ziqin Zhou
    DBLP profile ↗ORCID search ↗
  3. LLM2CLIP: Powerful Language Model Unlocks Richer Cross-Modality Representation
    AAAI 2026 ·
    Weiquan Huang
    DBLP profile ↗ORCID search ↗
  4. MageBench: Bridging Large Multimodal Models to Agents
    WACV 2026 ·
    Miaosen Zhang
    DBLP profile ↗ORCID search ↗
  5. Aid: Adapting Image2video Diffusion Models for Instruction-Guided Video Prediction
    ICCV 2025 ·
    Zhen Xing
    DBLP profile ↗ORCID search ↗
  6. FaceA-Net: Facial Attribute-Driven ID Preserving Image Generation Network
    AAAI 2025 ·
    Jiayu Wang
    DBLP profile ↗ORCID search ↗
  7. FloVD: Optical Flow Meets Video Diffusion Model for Enhanced Camera-Controlled Video Synthesis
    CVPR 2025 ·
    Wonjoon Jin
    DBLP profile ↗ORCID search ↗
  8. HomoGen: Enhanced Video Inpainting via Homography Propagation and Diffusion
    CVPR 2025 ·
    Ding Ding
    DBLP profile ↗ORCID search ↗
  9. JointDiT: Enhancing RGB-Depth Joint Modeling with Diffusion Transformers
    ICCV 2025 ·
    Byung-Ki Kwon
    DBLP profile ↗ORCID search ↗
  10. MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance
    ICCV 2025 ·
    Quanhao Li
    DBLP profile ↗ORCID search ↗
  11. MotionFollower: Editing Video Motion via Score-Guided Diffusion
    ICCV 2025 ·
    Shuyuan Tu
    DBLP profile ↗ORCID search ↗
  12. REDUCIO! Generating 1K Video Within 16 Seconds Using Extremely Compressed Motion Latents
    ICCV 2025 ·
    Rui Tian
    DBLP profile ↗ORCID search ↗
  13. Securing the Skies: A Comprehensive Survey on Anti-UAV Methods, Benchmarking, and Future Directions
    CVPR 2025 ·
    Yifei Dong
    DBLP profile ↗ORCID search ↗
  14. StableAnimator: High-Quality Identity-Preserving Human Image Animation
    CVPR 2025 ·
    Shuyuan Tu
    DBLP profile ↗ORCID search ↗
  15. UCDR-Adapter: Exploring Adaptation of Pre-Trained Vision-Language Models for Universal Cross-Domain Retrieval
    WACV 2025 ·
    Haoyu Jiang
    DBLP profile ↗ORCID search ↗
  16. ART•V: Auto-Regressive Text-to-Video Generation with Diffusion Models
    CVPR 2024 ·
    Wenming Weng
    DBLP profile ↗ORCID search ↗
  17. Aligning Vision Models with Human Aesthetics in Retrieval: Benchmarks and Algorithms
    NeurIPS 2024 ·
    Miaosen Zhang
    DBLP profile ↗ORCID search ↗
  18. BlockGCN: Redefine Topology Awareness for Skeleton-Based Action Recognition
    CVPR 2024 ·
    Yuxuan Zhou
    DBLP profile ↗ORCID search ↗
  19. Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions
    NeurIPS 2024 ·
    Heng Li
    DBLP profile ↗ORCID search ↗
  20. MicroCinema: A Divide-and-Conquer Approach for Text-to-Video Generation
    CVPR 2024 ·
    Yanhui Wang
    DBLP profile ↗ORCID search ↗
  21. MotionEditor: Editing Video Motion via Content-Aware Diffusion
    CVPR 2024 ·
    Shuyuan Tu
    DBLP profile ↗ORCID search ↗
  22. SimDA: Simple Diffusion Adapter for Efficient Video Generation
    CVPR 2024 ·
    Zhen Xing
    DBLP profile ↗ORCID search ↗