papers

Publications (49)

cs.CL2019

RLTM: An Efficient Neural IR Framework for Long Documents

Chen Zheng, Yu Sun, Shengxian Wan +1

Deep neural networks have achieved significant improvements in information retrieval (IR). However, most existing models are computational costly and can not efficiently scale to l…

cs.CL2024

NACL: A General and Effective KV Cache Eviction Framework for LLMs at Inference Time

Yilong Chen, Guoxia Wang, Junyuan Shang +7

Large Language Models (LLMs) have ignited an innovative surge of AI applications, marking a new era of exciting possibilities equipped with extended context windows. However, hosti…

cs.AI2023

Label Information Enhanced Fraud Detection against Low Homophily in Graphs

Yuchen Wang, Jinghui Zhang, Zhengjie Huang +9

Node classification is a substantial problem in graph-based fraud detection. Many existing works adopt Graph Neural Networks (GNNs) to enhance fraud detectors. While promising, cur…

cs.CL2026

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry

Yehan Yang, Junyuan Shang, Yang Li +3

Long-context LLM inference is bottlenecked by quadratic attention computation and growing KV-cache costs. Existing sparse attention and KV-compression methods typically decide whic…

cs.CL2020

Distilling Knowledge from Pre-trained Language Models via Text Smoothing

Xing Wu, Yibing Liu, Xiangyang Zhou +1

This paper studies compressing pre-trained language models, like BERT (Devlin et al.,2019), via teacher-student knowledge distillation. Previous works usually force the student mod…

cs.LG2025

SeWA: Selective Weight Average via Probabilistic Masking

Peng Wang, Shengchao Hu, Zerui Tao +5

Weight averaging has become a standard technique for enhancing model performance. However, methods such as Stochastic Weight Averaging (SWA) and Latest Weight Averaging (LAWA) ofte…