Xinyu Tian

xytian1008's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper 2 months ago

All Roads Lead to Rome: Incentivizing Divergent Thinking in Vision-Language Models

Paper • 2604.00479 • Published Apr 1 • 69

submitted a paper to Daily Papers 2 months ago

All Roads Lead to Rome: Incentivizing Divergent Thinking in Vision-Language Models

Paper • 2604.00479 • Published Apr 1 • 69

authored a paper 8 months ago

More Thought, Less Accuracy? On the Dual Nature of Reasoning in Vision-Language Models

Paper • 2509.25848 • Published Sep 30, 2025 • 81

authored 3 papers 10 months ago

ArGue: Attribute-Guided Prompt Tuning for Vision-Language Models

Paper • 2311.16494 • Published Nov 27, 2023 • 1

Identifying and Mitigating Position Bias of Multi-image Vision-Language Models

Paper • 2503.13792 • Published Mar 18, 2025 • 1

Black Sheep in the Herd: Playing with Spuriously Correlated Attributes for Vision-Language Recognition

Paper • 2502.15809 • Published Feb 19, 2025 • 1