Vineeth Balasubramanian

Research focus

Reasoning & Chain-of-Thought (2)Multimodal Models (1)Constitutional AI & AI Ethics (1)Eval Frameworks & Benchmarks (1)

Frequent co-authors

Kunal Tilaganji (2)Nagarajan Natarajan (2)Amit Sharma (2)Rohit Sinha (1)

Papers (2)

Aug 11, 2026

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

Disagreement among verifiers can be a powerful signal for identifying errors in multimodal reasoning, leading to a 5.95% performance boost without any training.

Rohit Sinha, Kunal Tilaganji, Tanuja Ganu +3

Multimodal Models Reasoning & Chain-of-Thought

IIT1w ago·also Microsoft Research, SCB Dental College and Hospital

Rethinking LLM Verification: Evidence Structure, Uncertainty, and Selective Refinement

Abstaining from uncertain predictions can enhance LLM accuracy in medical applications by 9.6 percentage points, transforming uncertainty into a strategic advantage.

Uma Ranjan, Kunal Tilaganji, Aditya Koul +9

Constitutional AI & AI Ethics Eval Frameworks & Benchmarks Reasoning & Chain-of-Thought

Search

Vineeth Balasubramanian

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)