← Search

Sanjay Lall

2 accepted papers

2026

Beyond Binary Preferences: A Principled Framework for Reward Modeling with Ordinal Feedback

ICLR 2026poster

Reward modeling is crucial for aligning large language models with human preferences, yet current approaches lack a principled mathematical framework for leveraging ordinal preference data. When human annotators provide graded preferences on a Likert scale (e.g., significantly better, better, slight…

Cited by 0SourceScholar
2025

LORE: Lagrangian-Optimized Robust Embeddings for Visual Encoders

NeurIPS 2025poster

Visual encoders have become fundamental components in modern computer vision pipelines. However, ensuring robustness against adversarial perturbations remains a critical challenge. Recent efforts have explored both supervised and unsupervised adversarial fine-tuning strategies. We identify two key l…

Cited by 0SourcecodeScholar