3 citations · 6 across the 17 of their papers we have counts for
4 papers · 1 filter
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…
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…
BAPFL: Exploring Backdoor Attacks Against Prototype-based Federated Learning
Honghong Zeng, Jiong Lou, Zhe Wang +4
Prototype-based federated learning (PFL) has emerged as a promising paradigm to address data heterogeneity problems in federated learning, as it leverages mean feature vectors as p…
Robust and Communication-Efficient Federated Domain Adaptation via Random Features
Zhanbo Feng, Yuanjie Wang, Jie Li +5
Modern machine learning (ML) models have grown to a scale where training them on a single machine becomes impractical. As a result, there is a growing trend to leverage federated l…