Saumitra Mishra

Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs

Finding Better Prototypes For Interpretable Text Classifiers With LLM Optimization

Interpreting Language Reward Models via Contrastive Explanations

Cross-Domain Graph Data Scaling: A Showcase with Diffusion Models

Representation Consistency for Accurate and Coherent LLM Answer Aggregation

To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models

Quantifying Prediction Consistency Under Fine-tuning Multiplicity in Tabular LLMs

Cross-Domain Graph Data Scaling: A Showcase with Diffusion Models

Quantifying Prediction Consistency Under Model Multiplicity in Tabular LLMs