collaborators

20 papers

cs.AI2026

VERDICT: Training-Free Step-Wise Verification of Multimodal Reasoning via Disagreement-Aware Consensus

Rohit Sinha, Kunal Tilaganji, Tanuja Ganu +3

Multimodal large language models often generate reasoning chains containing subtle errors that lead to incorrect answers. Current verification approaches have notable limitations.…

cs.AI2026

CPO: Evaluating Cross-Modal Composition and Counterfactual Performance in Omnimodal Models

Swapnanil Mukherjee, Agyeya Negi, Tanuja Ganu +1

Current Multimodal Large Language Models (MLLMs) can process diverse sensory inputs, yet their reasoning remains heavily biased toward a dominant modality, resulting in brittle cro…

cs.CV2026

CARE-X: Towards Clinically Useful Radiology VLMs with Auxiliary Supervision, Reward-Aligned Learning, and Tool-Augmented Measurement

Mercy Prasanna Ranjit, Anirban Porya, Sathvik Joel +8

A clinically useful chest X-ray system must go beyond fluent report generation: it should classify findings with tunable decision thresholds, localize them spatially, and derive th…

cs.AI2026

Reason, Reward, Refine: Step-Level Errors Corrections with Structured Feedback for Physics Reasoning in Small Language Models

Raj Jaiswal, Dhruv Jain, Rishabh Dhawan +4

Physics reasoning fails structurally in small language models: an error at any step propagates forward, corrupting every inference that follows. Limited domain knowledge, hallucina…

cs.SE2026

Obey, Diverge, Collapse: Blind Obedience to Incorrect Instructions Drives Code LLMs to Irrecoverable Code Semantic Collapse

Raj Jaiswal, Anany Singh Divy, Savar Bhasin +3

Code language models are now trusted collaborators in production workflows for debugging, refactoring, and iterative repair, and every benchmark that evaluates them assumes the ins…

cs.CV2026

Cascaded Sparse Autoencoders Learn Multi-Level Visual Concepts in Multimodal LLMs

Yusong Zhao, Hengyi Wang, Tanuja Ganu +2

Multimodal Large Language Models (MLLMs) have demonstrated strong performance on vision-language tasks, yet their internal visual representations remain difficult to interpret. Spa…