activity
20242026
collaborators

8 papers

cs.LG2026

MosaicQuant: Inlier-Outlier Disaggregation for Unified 4-Bit LLM Quantization

Yangjia Hu, Haodong Wang, Zicong Hong +8

4-bit quantization significantly reduces the memory footprint and accelerates the inference of large language models (LLMs). However, its limited bit-width representation struggles…

cs.DC2026

TwinQuant: Learnable Subspace Decomposition for 4-Bit LLM Quantization

Haodong Wang, Junjie Liu, Zicong Hong +4

4-bit quantization reduces the memory footprint and latency of large language model inference, but its aggressive precision reduction can severely degrade accuracy. Prior methods a…

cs.CR2026

DualSentinel: A Lightweight Framework for Detecting Targeted Attacks in Black-box LLM via Dual Entropy Lull Pattern

Xiaoyi Pang, Xuanyi Hao, Pengyu Liu +3

Recent intelligent systems integrate powerful Large Language Models (LLMs) through APIs, but their trustworthiness may be critically undermined by targeted attacks like backdoor an…

cs.CV2026

UNICBench: UNIfied Counting Benchmark for MLLM

Chenggang Rong, Tao Han, Zhiyuan Zhao +5

Counting is a core capability for multimodal large language models (MLLMs), yet there is no unified counting dataset to rigorously evaluate this ability across image, text, and aud…

cs.CL2025

DiEP: Adaptive Mixture-of-Experts Compression through Differentiable Expert Pruning

Sikai Bai, Haoxi Li, Jie Zhang +2

Despite the significant breakthrough of Mixture-of-Experts (MoE), the increasing scale of these MoE models presents huge memory and storage challenges. Existing MoE pruning methods…

cs.DC2025

DMoE: Dual Routing and Dynamic Scheduling for Efficient On-Device MoE-based LLM Serving

Haodong Wang, Qihua Zhou, Zicong Hong +1

The mixture of experts (MoE) model is a sparse variant of large language models (LLMs), designed to hold a better balance between intelligent capability and computational overhead.…