195 citations · 458 across the 33 of their papers we have counts for
34 papers
FedOBP: Federated Optimal Brain Personalization through Cloud-Edge Element-wise Decoupling
Xingyan Chen, Tian Du, Changqiao Xu +4
Federated Learning (FL) faces challenges from client data heterogeneity and resource-constrained mobile devices, which can degrade model accuracy. Personalized Federated Learning (…
RPS: Information Elicitation with Reinforcement Prompt Selection
Tao Wang, Jingyao Lu, Xibo Wang +5
Large language models (LLMs) have shown remarkable capabilities in dialogue generation and reasoning, yet their effectiveness in eliciting user-known but concealed information in o…
Graph Tokenization for Bridging Graphs and Transformers
Zeyuan Guo, Enmao Diao, Cheng Yang +1
The success of large pretrained Transformers is closely tied to tokenizers, which convert raw input into discrete symbols. Extending these models to graph-structured data remains a…
A Kinetic Energy Perspective of Flow Matching
Ziyun Li, Huancheng Hu, Soon Hoe Lim +6
Flow-based generative models can be viewed through a physics lens: sampling transports a particle from noise to data by integrating a learned velocity field, and each sample corres…
Think Before You Prune: Self-Reflective Structured Pruning for Reasoning Language Models
Ziyan Wang, Enmao Diao, Qi Le +5
Reasoning LLMs (RLMs) such as OpenAI o1, DeepSeek-R1, and Qwen3 deliver strong multi-step reasoning through chain-of-thought generation, but their large model sizes and lengthy dec…
Toward Unifying Group Fairness Evaluation from a Sparsity Perspective
Zhecheng Sheng, Jiawei Zhang, Enmao Diao
Ensuring algorithmic fairness remains a significant challenge in machine learning, particularly as models are increasingly applied across diverse domains. While numerous fairness c…
From Local to Global: Revisiting Structured Pruning Paradigms for Large Language Models
Ziyan Wang, Enmao Diao, Qi Le +6
Structured pruning is a practical approach to deploying large language models (LLMs) efficiently, as it yields compact, hardware-friendly architectures. However, the dominant local…
OBCache: Optimal Brain KV Cache Pruning for Efficient Long-Context LLM Inference
Yuzhe Gu, Xiyu Liang, Jiaojiao Zhao +1
Large language models (LLMs) with extended context windows enable powerful applications but impose significant memory overhead, as caching all key-value (KV) states scales linearly…
Probe Pruning: Accelerating LLMs through Dynamic Pruning via Model-Probing
Qi Le, Enmao Diao, Ziyan Wang +4
We introduce Probe Pruning (PP), a novel framework for online, dynamic, structured pruning of Large Language Models (LLMs) applied in a batch-wise manner. PP leverages the insight…
MAP: Multi-Human-Value Alignment Palette
Xinran Wang, Qi Le, Ammar Ahmed +5
Ensuring that generative AI systems align with human values is essential but challenging, especially when considering multiple human values and their potential trade-offs. Since hu…
DynamicFL: Federated Learning with Dynamic Communication Resource Allocation
Qi Le, Enmao Diao, Xinran Wang +3
Federated Learning (FL) is a collaborative machine learning framework that allows multiple users to train models utilizing their local data in a distributed manner. However, consid…
Robust Score-Based Quickest Change Detection
Sean Moushegian, Suya Wu, Enmao Diao +3
Methods in the field of quickest change detection rapidly detect in real-time a change in the data-generating distribution of an online data stream. Existing methods have been able…
ColA: Collaborative Adaptation with Gradient Learning
Enmao Diao, Qi Le, Suya Wu +4
A primary function of back-propagation is to compute both the gradient of hidden representations and parameters for optimization with gradient descent. Training large models requir…
ESC: Efficient Speech Coding with Cross-Scale Residual Vector Quantized Transformers
Yuzhe Gu, Enmao Diao
Neural speech codecs aim to compress input signals into minimal bits while maintaining content quality in a low-latency manner. However, existing neural codecs often trade model co…
Large Deviation Analysis of Score-based Hypothesis Testing
Enmao Diao, Taposh Banerjee, Vahid Tarokh
Score-based statistical models play an important role in modern machine learning, statistics, and signal processing. For hypothesis testing, a score-based hypothesis test is propos…
Robust Quickest Change Detection for Unnormalized Models
Suya Wu, Enmao Diao, Taposh Banerjee +2
Detecting an abrupt and persistent change in the underlying distribution of online data streams is an important problem in many applications. This paper proposes a new robust score…
Semi-Supervised Federated Learning for Keyword Spotting
Enmao Diao, Eric W. Tramel, Jie Ding +1
Keyword Spotting (KWS) is a critical aspect of audio-based applications on mobile devices and virtual assistants. Recent developments in Federated Learning (FL) have significantly…
Pruning Deep Neural Networks from a Sparsity Perspective
Enmao Diao, Ganghua Wang, Jiawei Zhan +3
In recent years, deep network pruning has attracted significant attention in order to enable the rapid deployment of AI into small devices with computation and memory constraints.…
Quickest Change Detection for Unnormalized Statistical Models
Suya Wu, Enmao Diao, Taposh Banerjee +2
Classical quickest change detection algorithms require modeling pre-change and post-change distributions. Such an approach may not be feasible for various machine learning models b…
Personalized Federated Recommender Systems with Private and Partially Federated AutoEncoders
Qi Le, Enmao Diao, Xinran Wang +3
Recommender Systems (RSs) have become increasingly important in many application domains, such as digital marketing. Conventional RSs often need to collect users' data, centralize…
A Theoretical Understanding of Neural Network Compression from Sparse Linear Approximation
Wenjing Yang, Ganghua Wang, Jie Ding +1
The goal of model compression is to reduce the size of a large neural network while retaining a comparable performance. As a result, computation and memory costs in resource-limite…
A Physics-Informed Vector Quantized Autoencoder for Data Compression of Turbulent Flow
Mohammadreza Momenifar, Enmao Diao, Vahid Tarokh +1
Analyzing large-scale data from simulations of turbulent flows is memory intensive, requiring significant resources. This major challenge highlights the need for data compression t…
Emulating Spatio-Temporal Realizations of Three-Dimensional Isotropic Turbulence via Deep Sequence Learning Models
Mohammadreza Momenifar, Enmao Diao, Vahid Tarokh +1
We use a data-driven approach to model a three-dimensional turbulent flow using cutting-edge Deep Learning techniques. The deep learning framework incorporates physical constraints…
Decentralized Multi-Target Cross-Domain Recommendation for Multi-Organization Collaborations
Enmao Diao, Vahid Tarokh, Jie Ding
Recommender Systems (RSs) are operated locally by different organizations in many realistic scenarios. If various organizations can fully share their data and perform computation i…