collaborators

6 papers

cs.LG2026

Ensembling Sparse Autoencoders

Soham Gadgil, Chris Lin, Su-In Lee

Sparse autoencoders (SAEs) are used to decompose neural network activations into human-interpretable features. Typically, features learned by a single SAE are used for downstream a…

cs.LG2026

A Geometric View for Understanding Concept Learning and Neuron Interpretation in Sparse Autoencoders

Chenhao Zhang, Chris Lin, Su-In Lee

We propose a unified mathematical framework for a geometric understanding of concept learning and neuron interpretation in sparse autoencoders (SAEs). While SAEs improve interpreta…

cs.LG2026

SurrogateSHAP: Training-Free Contributor Attribution for Text-to-Image (T2I) Models

Mingyu Lu, Soham Gadgil, Chris Lin +2

As Text-to-Image (T2I) diffusion models are increasingly used in real-world creative workflows, a principled framework for valuing contributors who provide a collection of data is…

cs.MA2026

Agents that Matter: Optimizing Multi-Agent LLMs via Removal-Based Attribution

Mingyu Lu, Yushan Huang, Chris Lin +1

As multi-agent systems (MAS) become increasingly complex, identifying the contributions of individual agents is critical for system optimization. However, existing approaches lack…

cs.LG2026

Where to Steer: Input-Dependent Layer Selection for Steering Improves LLM Alignment

Soham Gadgil, Chris Lin, Su-In Lee

Steering vectors have emerged as a lightweight and effective approach for aligning large language models (LLMs) at inference time, enabling modulation over model behaviors by shift…

cs.LG2025

An Efficient Framework for Crediting Data Contributors of Diffusion Models

Chris Lin, Mingyu Lu, Chanwoo Kim +1

As diffusion models are deployed in real-world settings, and their performance is driven by training data, appraising the contribution of data contributors is crucial to creating i…