collaborators

12 papers

cs.CR2026

When Context Bites: Detecting RAG Poisoning via Document-Level Attention Collapse

Yingtao Ren, Ziyi Zhao, Yiwei Fu +3

Retrieval-augmented generation (RAG) is indispensable for enhancing large language models. However, RAGs are increasingly susceptible to poisoning attacks, in which adversarial doc…

cs.CV2026

Von Mises-Fisher Mixture Model with Dynamic Shrinkage for Realistic Test-Time Transduction

Jiazhen Huang, Zhiming Liu, Changhu Wang +3

A range of methods aim to enhance the performance of vision-language models (VLMs) at test time. Among them, transduction has emerged as a promising paradigm due to its strong comp…

cs.LG2026

A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions

Zhiyin Yu, Yuchen Mou, Juncheng Yan +17

Reinforcement learning (RL) has emerged as a powerful post-training paradigm for enhancing the reasoning capabilities of large language models (LLMs). However, reinforcement learni…

cs.LG2026

DREAM: Dual-Standard Semantic Homogeneity with Dynamic Optimization for Graph Learning with Label Noise

Yusheng Zhao, Jiaye Xie, Qixin Zhang +5

Graph neural networks (GNNs) have been widely used in various graph machine learning scenarios. Existing literature primarily assumes well-annotated training graphs, while the reli…

cs.LG2025

A Survey of Graph Neural Networks in Real world: Imbalance, Noise, Privacy and OOD Challenges

Wei Ju, Siyu Yi, Yifan Wang +10

Graph-structured data exhibits universality and widespread applicability across diverse domains, such as social network analysis, biochemistry, financial fraud detection, and netwo…

cs.CL2025

A Survey on Efficient Large Language Model Training: From Data-centric Perspectives

Junyu Luo, Bohan Wu, Xiao Luo +8

Post-training of Large Language Models (LLMs) is crucial for unlocking their task generalization potential and domain-specific capabilities. However, the current LLM post-training…