9 citations · 28 across the 19 of their papers we have counts for
22 papers
SEPO: Evidence-Grounded Prompt Optimization via Structural Editing
Xiaoyu Ma, Haoyue Liu, Yiwen Li +4
Existing API-only prompt optimisers are often described as interpretable, but in practice, this usually means only post-hoc inspectability: each iteration still rewrites the prompt…
One Rewrite to Fix Them All? Type-Aware Repair Allocation for Text-to-Image Prompt Optimization
Haoyue Liu, Xiaoyu Ma, Ye Chen +2
Text-to-image (T2I) generators often fail to follow their prompts faithfully, producing wrong counts, swapped attributes, ambiguous relations, and illegible text. Prompt optimizati…
Select Smarter, Not More: Prompt-Aware Evaluation Scheduling with Submodular Guarantees
Xiaoyu Ma, Yiwen Li, Haoyue Liu +4
Automatic prompt optimization (APO) hinges on the quality of its evaluation signal, yet scoring every prompt candidate on the full training set is prohibitively expensive. Existing…
Adaptive Prompt Structure Factorization: A Framework for Self-Discovering and Optimizing Compositional Prompt Programs
Haoyue Liu, Zhichao Wang, Yongxin Guo +2
Automated prompt optimization is crucial for eliciting reliable reasoning from large language models (LLMs), yet most API-only prompt optimizers iteratively edit monolithic prompts…
PIDP-Attack: Combining Prompt Injection with Database Poisoning Attacks on Retrieval-Augmented Generation Systems
Haozhen Wang, Haoyue Liu, Jionghao Zhu +3
Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of applications. However, their practical deployment is often hindered by issues such as o…
Multi-Physics: A Comprehensive Benchmark for Multimodal LLMs Reasoning on Chinese Multi-Subject Physics Problems
Zhongze Luo, Zhenshuai Yin, Yongxin Guo +3
While multimodal LLMs (MLLMs) demonstrate remarkable reasoning progress, their application in specialized scientific domains like physics reveals significant gaps in current evalua…
GRPO-A: Guided Group Relative Policy Optimization with Adaptive Guidance
Yongxin Guo, Wenbo Deng, Zhenglin Cheng +1
Reinforcement Learning with Verifiable Rewards (RLVR) has markedly enhanced the reasoning abilities of large language models (LLMs). Its success, however, largely depends on strong…
FedMABA: Towards Fair Federated Learning through Multi-Armed Bandits Allocation
Zhichao Wang, Lin Wang, Yongxin Guo +2
The increasing concern for data privacy has driven the rapid development of federated learning (FL), a privacy-preserving collaborative paradigm. However, the statistical heterogen…
TRACE: Temporal Grounding Video LLM via Causal Event Modeling
Yongxin Guo, Jingyu Liu, Mingda Li +3
Video Temporal Grounding (VTG) is a crucial capability for video understanding models and plays a vital role in downstream tasks such as video browsing and editing. To effectively…
Save It All: Enabling Full Parameter Tuning for Federated Large Language Models via Cycle Block Gradient Descent
Lin Wang, Zhichao Wang, Xiaoying Tang
The advent of large language models (LLMs) has revolutionized the deep learning paradigm, yielding impressive results across a wide array of tasks. However, the pre-training or fin…
Smart Sampling: Helping from Friendly Neighbors for Decentralized Federated Learning
Lin Wang, Yang Chen, Yongxin Guo +1
Federated Learning (FL) is gaining widespread interest for its ability to share knowledge while preserving privacy and reducing communication costs. Unlike Centralized FL, Decentra…
Client2Vec: Improving Federated Learning by Distribution Shifts Aware Client Indexing
Yongxin Guo, Lin Wang, Xiaoying Tang +1
Federated Learning (FL) is a privacy-preserving distributed machine learning paradigm. Nonetheless, the substantial distribution shifts among clients pose a considerable challenge…
Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models
Yongxin Guo, Zhenglin Cheng, Xiaoying Tang +2
The Sparse Mixture of Experts (SMoE) has been widely employed to enhance the efficiency of training and inference for Transformer-based foundational models, yielding promising resu…
VTG-LLM: Integrating Timestamp Knowledge into Video LLMs for Enhanced Video Temporal Grounding
Yongxin Guo, Jingyu Liu, Mingda Li +6
Video Temporal Grounding (VTG) strives to accurately pinpoint event timestamps in a specific video using linguistic queries, significantly impacting downstream tasks like video bro…
FedRec+: Enhancing Privacy and Addressing Heterogeneity in Federated Recommendation Systems
Lin Wang, Zhichao Wang, Xi Leng +1
Preserving privacy and reducing communication costs for edge users pose significant challenges in recommendation systems. Although federated learning has proven effective in protec…
Enhancing Clustered Federated Learning: Integration of Strategies and Improved Methodologies
Yongxin Guo, Xiaoying Tang, Tao Lin
Federated Learning (FL) is an evolving distributed machine learning approach that safeguards client privacy by keeping data on edge devices. However, the variation in data among cl…
Unifying and Personalizing Weakly-supervised Federated Medical Image Segmentation via Adaptive Representation and Aggregation
Li Lin, Jiewei Wu, Yixiang Liu +2
Federated learning (FL) enables multiple sites to collaboratively train powerful deep models without compromising data privacy and security. The statistical heterogeneity (e.g., no…
Entropy-driven Fair and Effective Federated Learning
Lin Wang, Zhichao Wang, Ye Shi +2
Federated Learning (FL) enables collaborative model training across distributed devices while preserving data privacy. Nonetheless, the heterogeneity of edge devices often leads to…
FedRC: Tackling Diverse Distribution Shifts Challenge in Federated Learning by Robust Clustering
Yongxin Guo, Xiaoying Tang, Tao Lin
Federated Learning (FL) is a machine learning paradigm that safeguards privacy by retaining client data on edge devices. However, optimizing FL in practice can be challenging due t…
Diversity Boosted Learning for Domain Generalization with Large Number of Domains
Xi Leng, Xiaoying Tang, Yatao Bian
Machine learning algorithms minimizing the average training loss usually suffer from poor generalization performance due to the greedy exploitation of correlations among the traini…
DELTA: Diverse Client Sampling for Fasting Federated Learning
Lin Wang, YongXin Guo, Tao Lin +1
Partial client participation has been widely adopted in Federated Learning (FL) to reduce the communication burden efficiently. However, an inadequate client sampling scheme can le…
FedBR: Improving Federated Learning on Heterogeneous Data via Local Learning Bias Reduction
Yongxin Guo, Xiaoying Tang, Tao Lin
Federated Learning (FL) is a way for machines to learn from data that is kept locally, in order to protect the privacy of clients. This is typically done using local SGD, which hel…