Xinyu Tian
- Papers
- 5
Cite
Notes
Only stored in your browser.
5papers
Authored papers
5All Roads Lead to Rome: Incentivizing Divergent Thinking in Vision-Language Models
arXiv 2026
More Thought, Less Accuracy? On the Dual Nature of Reasoning in Vision-Language Models
arXiv 2025
Identifying and Mitigating Position Bias of Multi-image Vision-Language Models
CVPR 2025 1
Speech Translation Refinement using Large Language Models
arXiv 2025
Black Sheep in the Herd: Playing with Spuriously Correlated Attributes for Vision-Language Recognition
arXiv 2025
Affiliations
No known affiliations.
Frequent co-authors
10from 5 papers