Pramod Viswanath

MURMUR: Using cross-user chatter to break collaborative language agents

AutoCode: LLMs as Problem Setters for Competitive Programming

TritonGym: A Benchmark for Agentic LLM Workflows in Triton GPU Code Generation

COPER: Agentic Context Significantly Improves and Stabilizes LLM in Multi-Player Game

OML: A Primitive for Reconciling Open Access with Owner Control in AI Model Distribution

Scalable Fingerprinting of Large Language Models

SPIN-Bench: How Well Do LLMs Plan Strategically and Reason Socially?