collaborators

15 papers

cs.MM2026

MPrune: Hierarchical Collaborative Pruning for Efficient Multi-Modal Multi-Agent Retrieval-Augmented Generation

Taolin Zhang, Weizi shao, Zijie Zhou +5

Recent advances in multi-modal retrieval-augmented generation (mRAG), which augments multi-modal large language models (MLLMs) with external knowledge, have shown that collective i…

cs.DC2026

Efficiency and Cost Alignment in Batched LLM Serving via Resource-Fair Scheduling

Dayi Yao, Zijie Zhou

This paper studies a resource-allocation inefficiency in batched large language model (LLM) serving: heterogeneous requests that share a decode batch impose max-driven computationa…

cs.AI2026

Online Linear Programming for Multi-Objective Routing in LLM Serving

Zixi Chen, Yinyu Ye, Zijie Zhou

We study the online routing problem in large language model serving, where requests arrive sequentially and must be dispatched to parallel decode workers under tight batch-size and…

math.OC2026

LLM Serving Optimization with Variable Prefill and Decode Lengths

Meixuan Wang, Yinyu Ye, Zijie Zhou

We study offline scheduling for large language model (LLM) serving under a fixed KV-cache memory budget, where requests have heterogeneous prompt (prefill) and response (decode) le…

cs.AI2026

Geometry-Aware Online Scheduling for LLM Serving: From Theoretical Bound to System Practice

Li Kong, Qi Qi, Yinyu Ye +1

The explosive demand for interactive Large Language Model serving has highlighted the management of the Key-Value cache's dynamic memory footprint as a critical area for performanc…

cs.AI2026

PolarMem: A Training-Free Polarized Latent Graph Memory for Verifiable Vision-Language Models

Zhisheng Chen, Tingyu Wu, Zijie Zhou +7

Memory is not merely a storage mechanism for intelligent systems, but a structure for organizing evidence and constraining belief. This is especially important for multimodal reaso…