Xia Hu

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

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

Get the GIST of Graphs with Intersection Signature

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

70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float (DFloat11)

Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference

Learning to Route LLMs with Confidence Tokens

MQuAKE-Remastered: Multi-Hop Knowledge Editing Can Only Be Advanced with Reliable Evaluations

Confident or Seek Stronger: Exploring Uncertainty-Based Small LM Routing From Benchmarking to Generalization

Advancing Table Understanding of Large Language Models via Feature Re-ordering

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

Graph Transformers Get the GIST: Graph Invariant Structural Trait for Refined Graph Encoding

STRUCTDROP: A STRUCTURED RANDOM ALGORITHM TOWARDS EFFICIENT LARGE-SCALE GRAPH TRAINING

Weighted Diversified Sampling for Efficient Data-Driven Single-Cell Gene-Gene Interaction Discovery