Hong Chen

The paper proposes DP-SelFT, a novel framework for differentially private selective fine-tuning that significantly improves the privacy-utility trade-off for LLMs by intelligently selecting robust parameter subsets.

The paper introduces Hierarchical Adaptive Budgeter (HAB), a framework that improves LLM reasoning efficiency by adaptively allocating computational resources to match the intrinsic complexity of both problems and individual reasoning steps.

The paper introduces Hierarchical Adaptive Budgeter (HAB), a framework that improves LLM reasoning efficiency by adaptively allocating computational resources to match the intrinsic complexity of both problems and individual reasoning steps.

This paper connects two approaches to safeguarding variable scopes in generated code by compiling a calculus with polymorphic environment classifiers to a CMTT-based calculus.