5 citations · 19 across the 17 of their papers we have counts for
18 papers
MoEGen: Mixture-of-Experts for Instance-Adaptive LoRA Generation
Yiming Zeng, Lei Lu, Zexin Li +10
Parameter-efficient fine-tuning (PEFT) enables efficient adaptation of large language models, but existing MoE-based PEFT methods typically improve capacity by storing multiple ful…
LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling
Tong Zheng, Haolin Liu, Chengsong Huang +10
Test-time scaling (TTS) has become an effective approach for improving large language model performance by allocating additional computation during inference. However, existing TTS…
AgenticRecTune: Multi-Agent with Self-Evolving Skillhub for Recommendation System Optimization
Xidong Wu, Yue Zhuan, Ruoqiao Wei +7
Modern large-scale recommendation systems are typically constructed as multi-stage pipelines, encompassing pre-ranking, ranking, and re-ranking phases. While traditional recommenda…
Privacy-Preserving LLMs Routing
Xidong Wu, Yukuan Zhang, Yuqiong Ji +3
Large language model (LLM) routing has emerged as a critical strategy to balance model performance and cost-efficiency by dynamically selecting services from various model provider…
TreeDiff: AST-Guided Code Generation with Diffusion LLMs
Yiming Zeng, Jinghan Cao, Zexin Li +7
Code generation is increasingly critical for real-world applications. Still, diffusion-based large language models continue to struggle with this demand. Unlike free-form text, cod…
Client-Centric Federated Adaptive Optimization
Jianhui Sun, Xidong Wu, Heng Huang +1
Federated Learning (FL) is a distributed learning paradigm where clients collaboratively train a model while keeping their own data private. With an increasing scale of clients and…
Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch
Xidong Wu, Shangqian Gao, Zeyu Zhang +5
Current techniques for deep neural network (DNN) pruning often involve intricate multi-step processes that require domain-specific expertise, making their widespread adoption chall…
On the Role of Server Momentum in Federated Learning
Jianhui Sun, Xidong Wu, Heng Huang +1
Federated Averaging (FedAvg) is known to experience convergence issues when encountering significant clients system heterogeneity and data heterogeneity. Server momentum has been p…
Leveraging Foundation Models to Improve Lightweight Clients in Federated Learning
Xidong Wu, Wan-Yi Lin, Devin Willmott +4
Federated Learning (FL) is a distributed training paradigm that enables clients scattered across the world to cooperatively learn a global model without divulging confidential data…
Unbiased Watermark for Large Language Models
Zhengmian Hu, Lichang Chen, Xidong Wu +3
The recent advancements in large language models (LLMs) have sparked a growing apprehension regarding the potential misuse. One approach to mitigating this risk is to incorporate w…
Solving a Class of Non-Convex Minimax Optimization in Federated Learning
Xidong Wu, Jianhui Sun, Zhengmian Hu +2
The minimax problems arise throughout machine learning applications, ranging from adversarial training and policy evaluation in reinforcement learning to AUROC maximization. To add…
Federated Conditional Stochastic Optimization
Xidong Wu, Jianhui Sun, Zhengmian Hu +3
Conditional stochastic optimization has found applications in a wide range of machine learning tasks, such as invariant learning, AUPRC maximization, and meta-learning. As the dema…
Serverless Federated AUPRC Optimization for Multi-Party Collaborative Imbalanced Data Mining
Xidong Wu, Zhengmian Hu, Jian Pei +1
Multi-party collaborative training, such as distributed learning and federated learning, is used to address the big data challenges. However, traditional multi-party collaborative…
Performance and Energy Consumption of Parallel Machine Learning Algorithms
Xidong Wu, Preston Brazzle, Stephen Cahoon
Machine learning models have achieved remarkable success in various real-world applications such as data science, computer vision, and natural language processing. However, model t…
Decentralized Riemannian Algorithm for Nonconvex Minimax Problems
Xidong Wu, Zhengmian Hu, Heng Huang
The minimax optimization over Riemannian manifolds (possibly nonconvex constraints) has been actively applied to solve many problems, such as robust dimensionality reduction and de…
Faster Adaptive Federated Learning
Xidong Wu, Feihu Huang, Zhengmian Hu +1
Federated learning has attracted increasing attention with the emergence of distributed data. While extensive federated learning algorithms have been proposed for the non-convex di…
Distributed Dynamic Safe Screening Algorithms for Sparse Regularization
Runxue Bao, Xidong Wu, Wenhan Xian +1
Distributed optimization has been widely used as one of the most efficient approaches for model training with massive samples. However, large-scale learning problems with both mass…
AdaGDA: Faster Adaptive Gradient Descent Ascent Methods for Minimax Optimization
Feihu Huang, Xidong Wu, Zhengmian Hu
In the paper, we propose a class of faster adaptive Gradient Descent Ascent (GDA) methods for solving the nonconvex-strongly-concave minimax problems by using the unified adaptive…