Jiayi Yuan

Who Routes the Router: Rethinking the Evaluation of LLM Routing Systems

RouterArena: An Open Platform for Comprehensive Comparison of LLM Routers

FAFO: Lossy KV Cache Compression for Lossless Inference Acceleration via Draftless Fumble Decoding

Interpreting and Steering LLMs with Mutual Information-based Explanations on Sparse Autoencoders

AutoL2S: Auto Long-Short Reasoning for Efficient Large Language Models

Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference

Interpreting and Steering LLM Representations with Mutual Information-based Explanations on Sparse Autoencoders

Attack on LLMs: LoRA Once, Backdoor Everywhere in the Share-and-Play Ecosystem