3 papers
cs.CV2026
When Language Overwrites Vision: Over-Alignment and Geometric Debiasing in Vision-Language Models
Harshvardhan Saini, Samyak Jha, Yiming Tang +1
Vision-Language Models (VLMs) increasingly power high-stakes applications, from medical imaging to autonomous systems, yet they routinely hallucinate, confidently describing conten…
cs.CV2026
CAPA: Contribution-Aware Pruning and FFN Approximation for Efficient Large Vision-Language Models
Samyak Jha, Junho Kim
Efficient inference in Large Vision-Language Models is constrained by the high cost of processing thousands of visual tokens, yet it remains unclear which tokens and computations c…
cs.CV2026
CRoPS: A Training-Free Hallucination Mitigation Framework for Vision-Language Models
Neeraj Anand, Samyak Jha, Udbhav Bamba +1
Despite the rapid success of Large Vision-Language Models (LVLMs), a persistent challenge is their tendency to generate hallucinated content, undermining reliability in real-world…