PPaperPicks

Gang Yu

StepFun

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

DBLP profile ↗ORCID 0000-0001-5570-2710 ↗Google Scholar ↗Homepage ↗

Venues

NeurIPS ×5CVPR ×4ICCV ×4AAAI ×3ACM MM ×2ECCV ×2ICLR ×2ACL ×1CHI ×1

Frequent coauthors

Jiaxu Zhang
DBLP profile ↗ORCID search ↗
×3
Yiying Yang
DBLP profile ↗ORCID search ↗
×3
Biao Jiang
DBLP profile ↗ORCID search ↗
×2
Yiwen Chen
DBLP profile ↗ORCID search ↗
×2
Sijin Chen
DBLP profile ↗ORCID search ↗
×2
Pengtao Chen
DBLP profile ↗ORCID search ↗
×1
Chi Zhang
DBLP profile ↗ORCID search ↗
×1
Yongqi Huang
DBLP profile ↗ORCID search ↗
×1
Chongjun Tu
DBLP profile ↗ORCID search ↗
×1
Wei Cheng
DBLP profile ↗ORCID search ↗
×1
Xinyao Liao
DBLP profile ↗ORCID search ↗
×1
Jingjing Chang
DBLP profile ↗ORCID search ↗
×1

Papers

  1. Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion Transformers
    AAAI 2026 ·
    Pengtao Chen
    DBLP profile ↗ORCID search ↗
  2. AppAgent: Multimodal Agents as Smartphone Users
    CHI 2025 ·
    Chi Zhang
    DBLP profile ↗ORCID search ↗
  3. Causal Motion Tokenizer for Streaming Motion Generation
    ICCV 2025 ·
    Biao Jiang
    DBLP profile ↗ORCID search ↗
  4. DeRS: Towards Extremely Efficient Upcycled Mixture-of-Experts Models
    CVPR 2025 ·
    Yongqi Huang
    DBLP profile ↗ORCID search ↗
  5. FAVOR-Bench: A Comprehensive Benchmark for Fine-Grained Video Motion Understanding
    NeurIPS 2025 ·
    Chongjun Tu
    DBLP profile ↗ORCID search ↗
  6. MVPaint: Synchronized Multi-View Diffusion for Painting Anything 3D
    CVPR 2025 ·
    Wei Cheng
    DBLP profile ↗ORCID search ↗
  7. MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers
    ICLR 2025 ·
    Yiwen Chen
    DBLP profile ↗ORCID search ↗
  8. MikuDance: Animating Character Art With Mixed Motion Dynamics
    ICCV 2025 ·
    Jiaxu Zhang
    DBLP profile ↗ORCID search ↗
  9. Motionagent: Fine-Grained Controllable Video Generation via Motion Field Agent
    ICCV 2025 ·
    Xinyao Liao
    DBLP profile ↗ORCID search ↗
  10. OmniSVG: A Unified Scalable Vector Graphics Generation Model
    NeurIPS 2025 ·
    Yiying Yang
    DBLP profile ↗ORCID search ↗
  11. OneIG-Bench: Omni-dimensional Nuanced Evaluation for Image Generation
    NeurIPS 2025 ·
    Jingjing Chang
    DBLP profile ↗ORCID search ↗
  12. SC-Captioner: Improving Image Captioning with Self-Correction by Reinforcement Learning
    ICCV 2025 ·
    Lin Zhang
    DBLP profile ↗ORCID search ↗
  13. Scene123: One Prompt to 3D Scene Generation via Video-Assisted and Consistency-Enhanced MAE
    ACM MM 2025 ·
    Yiying Yang
    DBLP profile ↗ORCID search ↗
  14. Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Generation
    NeurIPS 2025 ·
    Anlin Zheng
    DBLP profile ↗ORCID search ↗
  15. Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data
    ACL 2024 ·
    Yanda Li
    DBLP profile ↗ORCID search ↗
  16. Generative Motion Stylization of Cross-structure Characters within Canonical Motion Space
    ACM MM 2024 ·
    Jiaxu Zhang
    DBLP profile ↗ORCID search ↗
  17. IT3D: Improved Text-to-3D Generation with Explicit View Synthesis
    AAAI 2024 ·
    Yiwen Chen
    DBLP profile ↗ORCID search ↗
  18. LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning
    CVPR 2024 ·
    Sijin Chen
    DBLP profile ↗ORCID search ↗
  19. M3DBench: Towards Omni 3D Assistant with Interleaved Multi-modal Instructions
    ECCV 2024 ·
    Mingsheng Li
    DBLP profile ↗ORCID search ↗
  20. MeshXL: Neural Coordinate Field for Generative 3D Foundation Models
    NeurIPS 2024 ·
    Sijin Chen
    DBLP profile ↗ORCID search ↗
  21. MotionChain: Conversational Motion Controllers via Multimodal Prompts
    ECCV 2024 ·
    Biao Jiang
    DBLP profile ↗ORCID search ↗
  22. PM-INR: Prior-Rich Multi-Modal Implicit Large-Scale Scene Neural Representation
    AAAI 2024 ·
    Yiying Yang
    DBLP profile ↗ORCID search ↗
  23. Paint3D: Paint Anything 3D With Lighting-Less Texture Diffusion Models
    CVPR 2024 ·
    Xianfang Zeng
    DBLP profile ↗ORCID search ↗
  24. TapMo: Shape-aware Motion Generation of Skeleton-free Characters
    ICLR 2024 ·
    Jiaxu Zhang
    DBLP profile ↗ORCID search ↗