Scholar
Zhaoyang Wei
Google Scholar ID: CkgaTVAAAAAJ
University of Chinese Academy of Sciences
Computer vision
Point Prompt
Pointly Supervision
Weakly Supervision
Interactive Perception
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
23
H-index
1
i10-index
1
Publications
4
Co-authors
3
list available
Publications
11 items
CALR: Continuous Anchored Latent Reasoning via Render-of-Thought Compression
2026
Cited
0
Video-HolmesV2: Can MLLMs Reason with Spatio-Temporal Audio-Visual Evidence in Long Videos?
2026
Cited
0
Evidence-Grounded Trustworthy Multimodal Reasoning and Evaluation Benchmark in Complex Urban Scenes
2026
Cited
0
LUT: Latent Utility Training for Visual Reasoning
2026
Cited
0
What Makes VLMs Robust? Towards Reconciling Robustness and Accuracy in Vision-Language Models
2026
Cited
0
HeroGS: Hierarchical Guidance for Robust 3D Gaussian Splatting under Sparse Views
2026
Cited
0
SAPNet++: Evolving Point-Prompted Instance Segmentation with Semantic and Spatial Awareness
2026
Cited
0
Video Evidence to Reasoning Efficient Video Understanding via Explicit Evidence Grounding
2026
Cited
0
Load more
Co-authors
3 total
Zhenjun Han（韩振军）
University of Chinese Academy of Sciences
Xuehui Yu
University of Chinese Academy of Sciences， Phd
Guorong Li
University of Chinese Academy of Sciences
