Steerable Visual Representations
Paper • 2604.02327 • Published • 56
Varun Gupta
guptavarun
AI & ML interests
None yet
Organizations
upvoted a paper 3 months ago
upvoted 5
papers about 1 year ago
Vision Transformers Don't Need Trained Registers
Paper • 2506.08010 • Published • 22
What Makes a Good Natural Language Prompt?
Paper • 2506.06950 • Published • 11
The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity
Paper • 2506.06941 • Published • 17
Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling
Paper • 2504.13169 • Published • 39
VELOCITI: Benchmarking Video-Language Compositional Reasoning with Strict Entailment
Paper • 2406.10889 • Published • 2