3 papers
cs.CL2025
Robo-Instruct: Simulator-Augmented Instruction Alignment For Finetuning Code LLMs
Zichao Hu, Junyi Jessy Li, Arjun Guha +1
Code LLMs have shown promising results with converting tasks in natural language to programs that can be executed by service robots. We are interested in finetuning small, speciali…
cs.CL2025
Understanding How CodeLLMs (Mis)Predict Types with Activation Steering
Francesca Lucchetti, Arjun Guha
Large Language Models (LLMs) are widely used by software engineers for programming tasks. However, research shows that LLMs often lack a deep understanding of program semantics. Ev…
cs.LG2025
NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals
Jaden Fiotto-Kaufman, Alexander R. Loftus, Eric Todd +17
We introduce NNsight and NDIF, technologies that work in tandem to enable scientific study of the representations and computations learned by very large neural networks. NNsight is…