Peng Jin

Venues

Frequent coauthors

Papers

1. Next Patch Prediction for AutoRegressive Visual Generation
   AAAI 2026 ·

   Yatian Pang

   DBLP profile ↗ORCID search ↗
2. Aligning Instance Brownian Bridge with Texts for Open-Vocabulary Video Instance Segmentation
   AAAI 2025 ·

   Zesen Cheng

   DBLP profile ↗ORCID search ↗
3. LlaVA-CoT: Let Vision Language Models Reason Step-By-Step
   ICCV 2025 ·

   Guowei Xu

   DBLP profile ↗ORCID search ↗
4. MUSE: Mamba Is Efficient Multi-scale Learner for Text-video Retrieval
   AAAI 2025 ·

   Haoran Tang

   DBLP profile ↗ORCID search ↗
5. MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts
   ICLR 2025 · Peng Jin
6. MoH: Multi-Head Attention as Mixture-of-Head Attention
   ICML 2025 · Peng Jin
7. Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection
   ICML 2025 ·

   Zhiyuan Yan

   DBLP profile ↗ORCID search ↗
8. Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding
   CVPR 2024 · Peng Jin
9. FreestyleRet: Retrieving Images from Style-Diversified Queries
   ECCV 2024 ·

   Hao Li

   DBLP profile ↗ORCID search ↗
10. LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inference
    EMNLP 2024 ·

    Zhongwei Wan

    DBLP profile ↗ORCID search ↗
11. Local Action-Guided Motion Diffusion Model for Text-to-Motion Generation
    ECCV 2024 · Peng Jin
12. Parallel Vertex Diffusion for Unified Visual Grounding
    AAAI 2024 ·

    Zesen Cheng

    DBLP profile ↗ORCID search ↗
13. RAP: Efficient Text-Video Retrieval with Sparse-and-Correlated Adapter
    ACL 2024 ·

    Meng Cao

    DBLP profile ↗ORCID search ↗
14. Repaint123: Fast and High-Quality One Image to 3D Generation with Progressive Controllable Repainting
    ECCV 2024 ·

    Junwu Zhang

    DBLP profile ↗ORCID search ↗
15. Video-LLaVA: Learning United Visual Representation by Alignment Before Projection
    EMNLP 2024 ·

    Bin Lin

    DBLP profile ↗ORCID search ↗