12 papers
AgentSnare: Learning to Delay, Divert, and Defuse Autonomous Penetration Agents
Ruoyu Wang, Heng Zhao, Renjie Wu +4
Large language model (LLM) agents automate penetration testing through an observation-action loop, selecting actions based on observations returned by tools. This dependence allows…
REIN: Bridging the Gap between Reasoning and Reliability via Reflection and Abstention Alignment
Zhengze Huang, Luyang Yu, Di Hong +5
Large reasoning models (LRMs) are prone to hallucination, which undermines their reliability and poses challenges for safe deployment. Hallucinations in LRMs arise from two distinc…
Post-Training Shifts Confidence: A Three-Stage Analysis of How SFT, RL, and OPD Shape CoT Calibration
Shuhao Li, Guodong Du, Anhao Zhao +3
Large language models have made strong reasoning gains through supervised fine-tuning, reinforcement learning, and on-policy distillation, yet these post-training methods are usual…
Dynamic Model Merging Made Slim
Guodong Du, Wanyu Lin
Model merging consolidates independently fine-tuned checkpoints without joint training or access to task data. Dynamic methods retain task-specific capacity, but must divide a limi…
On optimal solutions of classical and sliced Wasserstein GANs with non-Gaussian data
Yu-Jui Huang, Hsin-Hua Shen, Yu-Chih Huang +2
The generative adversarial network (GAN) aims to approximate an unknown distribution via a parameterized neural network (NN). While GANs have been widely applied in reinforcement a…
The Compositional Architecture of Regret in Large Language Models
Xiangxiang Cui, Shu Yang, Tianjin Huang +3
Regret in Large Language Models refers to their explicit regret expression when presented with evidence contradicting their previously generated misinformation. Studying the regret…
Understanding and Mitigating Cross-lingual Privacy Leakage via Language-specific and Universal Privacy Neurons
Wenshuo Dong, Qingsong Yang, Shu Yang +5
Large Language Models (LLMs) trained on massive data capture rich information embedded in the training data. However, this also introduces the risk of privacy leakage, particularly…
Latent Imputation before Prediction: A New Computational Paradigm for De Novo Peptide Sequencing
Ye Du, Chen Yang, Nanxi Yu +3
De novo peptide sequencing is a fundamental computational technique for ascertaining amino acid sequences of peptides directly from tandem mass spectrometry data, eliminating the n…
Knowledge Fusion of Large Language Models Via Modular SkillPacks
Guodong Du, Zhuo Li, Xuanning Zhou +9
Cross-capability transfer is a key challenge in large language model (LLM) research, with applications in multi-task integration, model compression, and continual learning. Recent…
FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks
Jian Chen, Zehui Lin, Wanyu Lin +3
Recently, the practical needs of ``the right to be forgotten'' in federated learning gave birth to a paradigm known as federated unlearning, which enables the server to forget pers…
Faithful Interpretation for Graph Neural Networks
Lijie Hu, Tianhao Huang, Lu Yu +3
Currently, attention mechanisms have garnered increasing attention in Graph Neural Networks (GNNs), such as Graph Attention Networks (GATs) and Graph Transformers (GTs). It is not…
DPGAN: A Dual-Path Generative Adversarial Network for Missing Data Imputation in Graphs
Xindi Zheng, Yuwei Wu, Yu Pan +3
Missing data imputation poses a paramount challenge when dealing with graph data. Prior works typically are based on feature propagation or graph autoencoders to address this issue…