PPaperPicks

Li Niu

Shanghai Jiao Tong University, MoE Key Lab of Artificial Intelligence, China

21 papers at tracked venues · 19 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0003-1970-8634 ↗Google Scholar ↗Homepage ↗

Venues

AAAI ×6CVPR ×6ECCV ×2NeurIPS ×2ACL ×1ICCV ×1ICLR ×1ICML ×1WWW ×1

Frequent coauthors

Zhaohe Liao
DBLP profile ↗ORCID search ↗
×3
Shuochen Chang
DBLP profile ↗ORCID search ↗
×2
Junjie Chen
DBLP profile ↗ORCID search ↗
×2
Yuxuan Duan
DBLP profile ↗ORCID search ↗
×2
Qingyang Liu
DBLP profile ↗ORCID search ↗
×1
Jiaxuan Chen
DBLP profile ↗ORCID search ↗
×1
Qianli Ma
DBLP profile ↗ORCID search ↗
×1
Yujie Zhou
DBLP profile ↗ORCID search ↗
×1
Yichen Wang
DBLP profile ↗ORCID search ↗
×1
Haonan Zhao
DBLP profile ↗ORCID search ↗
×1
Bingjie Gao
DBLP profile ↗ORCID search ↗
×1
Qingyang Liu
DBLP profile ↗ORCID search ↗
×1

Papers

  1. Bridging Visual Dynamics and Narrative Reasoning: Multimodal Large Language Models for Short Drama Quality Assessment
    WWW 2026 ·
    Qingyang Liu
    DBLP profile ↗ORCID search ↗
  2. CareCom: Generative Image Composition with Calibrated Reference Features
    AAAI 2026 ·
    Jiaxuan Chen
    DBLP profile ↗ORCID search ↗
  3. D3ToM: Decider-Guided Dynamic Token Merging for Accelerating Diffusion MLLMs
    AAAI 2026 ·
    Shuochen Chang
    DBLP profile ↗ORCID search ↗
  4. Unlocking the Black Box of Latent Reasoning: An Interpretability-Guided Approach to Intervention
    ACL 2026 ·
    Shuochen Chang
    DBLP profile ↗ORCID search ↗
  5. Decouple-Then-Merge: Finetune Diffusion Models as Multi-Task Learning
    CVPR 2025 ·
    Qianli Ma
    DBLP profile ↗ORCID search ↗
  6. Divide and Conquer: Exploring Language-centric Tree Reasoning for Video Question-Answering
    ICML 2025 ·
    Zhaohe Liao
    DBLP profile ↗ORCID search ↗
  7. Light-a-Video: Training-Free Video Relighting via Progressive Light Fusion
    ICCV 2025 ·
    Yujie Zhou
    DBLP profile ↗ORCID search ↗
  8. Pedestrian Motion Reconstruction: A Large-scale Benchmark via Mixed Reality Rendering with Multiple Perspectives and Modalities
    ICLR 2025 ·
    Yichen Wang
    DBLP profile ↗ORCID search ↗
  9. Shadow Generation Using Diffusion Model with Geometry Prior
    CVPR 2025 ·
    Haonan Zhao
    DBLP profile ↗ORCID search ↗
  10. The Devil is in the Prompts: Retrieval-Augmented Prompt Optimization for Text-to-Video Generation
    CVPR 2025 ·
    Bingjie Gao
    DBLP profile ↗ORCID search ↗
  11. Weak-shot Keypoint Estimation via Keyness and Correspondence Transfer
    NeurIPS 2025 ·
    Junjie Chen
    DBLP profile ↗ORCID search ↗
  12. Align and Aggregate: Compositional Reasoning with Video Alignment and Answer Aggregation for Video Question-Answering
    CVPR 2024 ·
    Zhaohe Liao
    DBLP profile ↗ORCID search ↗
  13. COIN-Matting: Confounder Intervention for Image Matting
    ECCV 2024 ·
    Zhaohe Liao
    DBLP profile ↗ORCID search ↗
  14. DomainGallery: Few-shot Domain-driven Image Generation by Attribute-centric Finetuning
    NeurIPS 2024 ·
    Yuxuan Duan
    DBLP profile ↗ORCID search ↗
  15. Meta-Point Learning and Refining for Category-Agnostic Pose Estimation
    CVPR 2024 ·
    Junjie Chen
    DBLP profile ↗ORCID search ↗
  16. Painterly Image Harmonization by Learning from Painterly Objects
    AAAI 2024 · Li Niu
  17. Progressive Painterly Image Harmonization from Low-Level Styles to High-Level Styles
    AAAI 2024 · Li Niu
  18. Shadow Generation for Composite Image Using Diffusion Model
    CVPR 2024 ·
    Qingyang Liu
    DBLP profile ↗ORCID search ↗
  19. Shadow Generation with Decomposed Mask Prediction and Attentive Shadow Filling
    AAAI 2024 ·
    Xinhao Tao
    DBLP profile ↗ORCID search ↗
  20. Unsupervised Exposure Correction
    ECCV 2024 ·
    Ruodai Cui
    DBLP profile ↗ORCID search ↗
  21. WeditGAN: Few-Shot Image Generation via Latent Space Relocation
    AAAI 2024 ·
    Yuxuan Duan
    DBLP profile ↗ORCID search ↗