Dennis Wei

Dropping Just a Handful of Preferences Can Change Top Large Language Model Rankings

Scalable Circuit Learning for Interpreting Large Language Models

CoFrGeNet: Continued Fraction Architectures for Language Generation

Final-Model-Only Data Attribution with a Unifying View of Gradient-Based Methods

Fair Continuous Resource Allocation with Equality of Impact

Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning

Identifying Sub-networks in Neural Networks via Functionally Similar Representations