collaborators

8 papers

cs.AI2025

CXL-SpecKV: A Disaggregated FPGA Speculative KV-Cache for Datacenter LLM Serving

Dong Liu, Yanxuan Yu

Large Language Models (LLMs) have revolutionized natural language processing tasks, but their deployment in datacenter environments faces significant challenges due to the massive…

cs.LG2025

Boundary-Aware Adversarial Filtering for Reliable Diagnosis under Extreme Class Imbalance

Yanxuan Yu, Michael S. Hughes, Julien Lee +2

We study classification under extreme class imbalance where recall and calibration are both critical, for example in medical diagnosis scenarios. We propose AF-SMOTE, a mathematica…

cs.AI2025

Cognitive Load Traces as Symbolic and Visual Accounts of Deep Model Cognition

Dong Liu, Yanxuan Yu

We propose \textbf{Cognitive Load Traces} (CLTs) as a mid-level interpretability framework for deep models, inspired by Cognitive Load Theory in human cognition. CLTs are defined a…

cs.AI2025

HSGM: Hierarchical Segment-Graph Memory for Scalable Long-Text Semantics

Dong Liu, Yanxuan Yu

Semantic parsing of long documents remains challenging due to quadratic growth in pairwise composition and memory requirements. We introduce \textbf{Hierarchical Segment-Graph Memo…

cs.DC2025

TinyServe: Query-Aware Cache Selection for Efficient LLM Serving

Dong Liu, Yanxuan Yu

Serving large language models (LLMs) efficiently remains challenging due to the high memory and latency overhead of key-value (KV) cache access during autoregressive decoding. We p…

cs.CL2025

SemToken: Semantic-Aware Tokenization for Efficient Long-Context Language Modeling

Dong Liu, Yanxuan Yu

Tokenization plays a critical role in language modeling, yet existing approaches such as Byte-Pair Encoding (BPE) or WordPiece operate purely on frequency statistics, ignoring the…