Arjun Guha

Agnostics: Learning to Synthesize Code in Any Programming Language with a Universal Reinforcement Learning Environment

AgentPack: A Dataset of Code Changes, Co-Authored by Agents and Humans

Robo-Instruct: Simulator-Augmented Instruction Alignment For Finetuning Code LLMs

NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals

ROBO-INSTRUCT: Simulator-Augmented Instruction Alignment For Finetuning Code LLMs