Zhengyang Liang

Venues

Frequent coauthors

Papers

1. Any Information Is Just Worth One Single Screenshot: Unifying Search With Visualized Information Retrieval
   ACL 2025 ·

   Zheng Liu

   DBLP profile ↗ORCID search ↗
2. Dynamic Self-adaptive Multiscale Distillation from Pre-trained Multimodal Large Model for Efficient Cross-modal Retrieval
   ACM MM 2025 · Zhengyang Liang
3. MLVU: Benchmarking Multi-task Long Video Understanding
   CVPR 2025 ·

   Junjie Zhou

   DBLP profile ↗ORCID search ↗
4. MomentSeeker: A Task-Oriented Benchmark For Long-Video Moment Retrieval
   NeurIPS 2025 ·

   Huaying Yuan

   DBLP profile ↗ORCID search ↗
5. Unveiling the Ignorance of MLLMs: Seeing Clearly, Answering Incorrectly
   CVPR 2025 ·

   Yexin Liu

   DBLP profile ↗ORCID search ↗
6. Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding
   CVPR 2025 ·

   Yan Shu

   DBLP profile ↗ORCID search ↗
7. AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning
   ICLR 2024 ·

   Yuwei Guo

   DBLP profile ↗ORCID search ↗
8. Self-Supervised Multi-Modal Knowledge Graph Contrastive Hashing for Cross-Modal Search
   AAAI 2024 ·

   Meiyu Liang

   DBLP profile ↗ORCID search ↗