460 citations · 535 across the 16 of their papers we have counts for
16 papers
KVMem: Virtualizing Million-Token Agent Workspaces on a Consumer GPU
Di Chai, Leye Wang, Zeshen Su +2
Modern LLM agents operate in persistent workspaces whose accumulated history can exceed both GPU KV capacity and the model's native context window. Existing systems typically compa…
PrefixFlow: Training-Time KV Caching for Schedule-Level Prefix Reuse in LLM RL Training
Pengbo Li, Feiyuan Zhang, Guangming Sheng +8
In reinforcement learning (RL) post-training, one prompt fans out into trajectories, yet standard trainers replay the shared prefix's forward and backward pass times; in lo…
DH-RAG: A Dynamic Historical Context-Powered Retrieval-Augmented Generation Method for Multi-Turn Dialogue
Feiyuan Zhang, Dezhi Zhu, James Ming +6
Retrieval-Augmented Generation (RAG) systems have shown substantial benefits in applications such as question answering and multi-turn dialogue \citep{lewis2020retrieval}. However,…
Unlocking Full Efficiency of Token Filtering in Large Language Model Training
Di Chai, Pengbo Li, Feiyuan Zhang +7
Token filtering has been proposed to enhance the utility of large language models (LLMs) by eliminating inconsequential tokens during training. While usingfewer tokens is expected…
PackVFL: Efficient HE Packing for Vertical Federated Learning
Liu Yang, Shuowei Cai, Di Chai +6
As an essential tool of secure distributed machine learning, vertical federated learning (VFL) based on homomorphic encryption (HE) suffers from severe efficiency problems due to d…
A Survey for Federated Learning Evaluations: Goals and Measures
Di Chai, Leye Wang, Liu Yang +3
Evaluation is a systematic approach to assessing how well a system achieves its intended purpose. Federated learning (FL) is a novel paradigm for privacy-preserving machine learnin…
UCTB: An Urban Computing Tool Box for Building Spatiotemporal Prediction Services
Jiangyi Fang, Liyue Chen, Di Chai +4
Spatiotemporal crowd flow prediction is one of the key technologies in smart cities. Currently, there are two major pain points that plague related research and practitioners. Firs…
A Survey on Vertical Federated Learning: From a Layered Perspective
Liu Yang, Di Chai, Junxue Zhang +6
Vertical federated learning (VFL) is a promising category of federated learning for the scenario where data is vertically partitioned and distributed among parties. VFL enriches th…
Secure Forward Aggregation for Vertical Federated Neural Networks
Shuowei Cai, Di Chai, Liu Yang +5
Vertical federated learning (VFL) is attracting much attention because it enables cross-silo data cooperation in a privacy-preserving manner. While most research works in VFL focus…
Practical and Secure Federated Recommendation with Personalized Masks
Liu Yang, Junxue Zhang, Di Chai +4
Federated recommendation addresses the data silo and privacy problems altogether for recommender systems. Current federated recommender systems mainly utilize cryptographic or obfu…
Aegis: A Trusted, Automatic and Accurate Verification Framework for Vertical Federated Learning
Cengguang Zhang, Junxue Zhang, Di Chai +1
Vertical federated learning (VFL) leverages various privacy-preserving algorithms, e.g., homomorphic encryption or secret sharing based SecureBoost, to ensure data privacy. However…
Practical Lossless Federated Singular Vector Decomposition over Billion-Scale Data
Di Chai, Leye Wang, Junxue Zhang +4
With the enactment of privacy-preserving regulations, e.g., GDPR, federated SVD is proposed to enable SVD-based applications over different data sources without revealing the origi…
FedEval: A Holistic Evaluation Framework for Federated Learning
Di Chai, Leye Wang, Liu Yang +3
Federated Learning (FL) has been widely accepted as the solution for privacy-preserving machine learning without collecting raw data. While new technologies proposed in the past fe…
Exploring the Generalizability of Spatio-Temporal Traffic Prediction: Meta-Modeling and an Analytic Framework
Leye Wang, Di Chai, Xuanzhe Liu +2
The Spatio-Temporal Traffic Prediction (STTP) problem is a classical problem with plenty of prior research efforts that benefit from traditional statistical learning and recent dee…
Secure Federated Matrix Factorization
Di Chai, Leye Wang, Kai Chen +1
To protect user privacy and meet law regulations, federated (machine) learning is obtaining vast interests in recent years. The key principle of federated learning is training a ma…
Bike Flow Prediction with Multi-Graph Convolutional Networks
Di Chai, Leye Wang, Qiang Yang
One fundamental issue in managing bike sharing systems is the bike flow prediction. Due to the hardness of predicting the flow for a single station, recent research works often pre…