Balaji Krishnamurthy

Social Agents: Collective Intelligence Improves LLM Predictions

Scaling Controllable Modeling Via Self-Evolving Feature Engineering

ExperiGen: Data Driven Hypothesis Generation with Experimental Verification

SPRO: Improving Image Generation via Self-Play

It Helps to Take a Second Opinion: Teaching Smaller LLMs To Deliberate Mutually via Selective Rationale Optimisation

Measuring And Improving Engagement of Text-to-Image Generation Models

Teaching Human Behavior Improves Content Understanding Abilities Of VLMs

Measuring And Improving Persuasiveness Of Large Language Models

Socia: Training Large Language Models To Simulate Social Constructs and Interventions