3 citations · 6 across the 17 of their papers we have counts for
6 papers · 1 filter
GateSight: Recurrent Memory Anticipates Attention Memory for Query-Agnostic KV Eviction in Hybrid LLMs
Junjie Li, Jiong Lou, Jie Li
Hybrid language models interleave Gated DeltaNet (GDN) layers, whose recurrent memory has a fixed size, with full-attention layers, whose key-value (KV) cache grows with the contex…
HeraSys: Collaborative Serving of Multiple LLM Workflows via Fine-Grained End-to-End Optimization
Size Li, Zhiqing Tang, Hongrui Liang +4
The proliferation of Large Language Models (LLMs) has shifted serving systems from processing isolated requests to orchestrating high-concurrency, multi-tenant agentic workflows. H…
IntentKV: Cross-Turn Intent-Aware KV Cache Pruning for Agent Inference
Junjie Li, Jiong Lou, Jie Li
Multi-turn LLM agents fan short queries into long trajectories of tool calls, search results, and intermediate reasoning. Both KV memory and KV read bandwidth grow by orders of mag…
OEP: Poisoning Self-Evolving LLM Agents via Locally Correct but Non-Transferable Experiences
Kaixiang Wang, Jiong Lou, Zhaojiacheng Zhou +1
Memory-augmented large language model (LLM) agents use iterative reflection and self-evolution to solve complex tasks, but these mechanisms introduce security risks. Existing agent…
ProxyKV: Cross-Model Proxy Pruning for Efficient Long-Context LLM Inference
Junjie Li, Jiong Lou, Jie Li
Efficient long-context inference in Large Language Models (LLMs) is severely constrained by the Key-Value (KV) cache memory wall, yet existing pruning methods force a choice betwee…
Federated Cross-Modal Retrieval with Missing Modalities via Semantic Routing and Adapter Personalization
Hefeng Zhou, Xuan Liu, Sicheng Chen +7
Federated cross-modal retrieval faces severe challenges from heterogeneous client data, particularly non-IID semantic distributions and missing modalities. Under such heterogeneity…