22 citations · 37 across the 28 of their papers we have counts for
30 papers
LexiconVLA: Learning Reusable Atomic Action Codebooks for Unseen Tasks
Zeming Wei, Jianheng Ye, Xinshuai Song +3
Vision-language-action (VLA) models struggle to reuse recurring interactions in unseen tasks. Our diagnostic study reveals that reliable task completion does not imply consistent e…
When Muon Optimizer Meets Adversarial Training: A Theoretical and Empirical Study
Jun Yan, Weiquan Huang, Jiankai Zuo +4
Adversarial training (AT) remains one of the most reliable empirical defenses against adversarial attacks. Its robustness critically depends on how the underlying min-max objective…
Symbolic-Neural Soft-Logic Reasoning: Towards Robust and Verifiable Thinking Chains via Cooperative Evolution
Rui Wang, Zeming Wei, Yihao Zhang +1
Large Language Models (LLMs) have demonstrated impressive progress in complex reasoning tasks, largely driven by the Chain-of-Thought (CoT) paradigm, which decomposes difficult pro…
SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces
Chang Jin, An Wang, Zeming Wei +7
Reusable skills are becoming a common interface for extending large language model agents, packaging procedural guidance with access to files, tools, memory, and execution environm…
Absorber LLM: Harnessing Causal Synchronization for Test-Time Training
Zhixin Zhang, Shabo Zhang, Chengcan Wu +2
Transformers suffer from a high computational cost that grows with sequence length for self-attention, making inference in long streams prohibited by memory consumption. Constant-m…
RACC: Representation-Aware Coverage Criteria for LLM Safety Testing
Zeming Wei, Zhixin Zhang, Chengcan Wu +3
Large Language Models (LLMs) face severe safety risks from jailbreak attacks, yet current safety testing largely relies on static datasets and lacks systematic criteria to evaluate…
Automata-Based Steering of Large Language Models for Diverse Structured Generation
Xiaokun Luan, Zeming Wei, Yihao Zhang +1
Large language models (LLMs) are increasingly tasked with generating structured outputs. While structured generation methods ensure validity, they often lack output diversity, a cr…
Stabilizing Multi-Attack Adversarial Training via Bandit Optimization
Rui Wang, Zeming Wei, Xiyue Zhang +1
Deep Neural Networks (DNNs) remain vulnerable to diverse adversarial perturbations, motivating multi-attack adversarial training (AT) for improved robustness. However, existing met…
Revisiting Hallucination Detection with Effective Rank-based Uncertainty
Rui Wang, Zeming Wei, Guanzhang Yue +1
Detecting hallucinations in large language models (LLMs) remains a fundamental challenge for their trustworthy deployment. Going beyond basic uncertainty-driven hallucination detec…
Securing Multi-Agent Systems Against Corruptions via Node Contribution Backpropagation
Chengcan Wu, Zhixin Zhang, Mingqian Xu +2
Multi-Agent Systems (MAS) have become a prevalent paradigm for Large Language Model (LLM) applications. However, the complex multi-agent design in MAS introduces unique trustworthi…
Dynamic Orthogonal Continual Fine-tuning for Mitigating Catastrophic Forgettings
Zhixin Zhang, Zeming Wei, Meng Sun
Catastrophic forgetting remains a critical challenge in continual learning for large language models (LLMs), where models struggle to retain performance on historical tasks when fi…
ReGA: Model-Based Safeguard for LLMs via Representation-Guided Abstraction
Zeming Wei, Chengcan Wu, Meng Sun
Large Language Models (LLMs) have achieved tremendous success in various tasks, yet concerns about their safety and security have emerged. In particular, they pose risks of generat…
Secure LLM Fine-Tuning via Safety-Aware Probing
Chengcan Wu, Zhixin Zhang, Zeming Wei +3
Large language models (LLMs) have achieved remarkable success across many applications, but their ability to generate harmful content raises serious safety concerns. Although safet…
3DAffordSplat: Efficient Affordance Reasoning with 3D Gaussians
Zeming Wei, Junyi Lin, Yang Liu +4
3D affordance reasoning is essential in associating human instructions with the functional regions of 3D objects, facilitating precise, task-oriented manipulations in embodied AI.…
MILE: A Mutation Testing Framework of In-Context Learning Systems
Zeming Wei, Yihao Zhang, Meng Sun
In-context Learning (ICL) has achieved notable success in the applications of large language models (LLMs). By adding only a few input-output pairs that demonstrate a new task, the…
Automata Extraction from Transformers
Yihao Zhang, Zeming Wei, Meng Sun
In modern machine (ML) learning systems, Transformer-based architectures have achieved milestone success across a broad spectrum of tasks, yet understanding their operational mecha…
A Theoretical Understanding of Self-Correction through In-context Alignment
Yifei Wang, Yuyang Wu, Zeming Wei +2
Going beyond mimicking limited human experiences, recent studies show initial evidence that, like humans, large language models (LLMs) are capable of improving their abilities pure…
Boosting Jailbreak Attack with Momentum
Yihao Zhang, Zeming Wei
Large Language Models (LLMs) have achieved remarkable success across diverse tasks, yet they remain vulnerable to adversarial attacks, notably the well-known jailbreak attack. In p…
Exploring the Robustness of In-Context Learning with Noisy Labels
Chen Cheng, Xinzhi Yu, Haodong Wen +4
Recently, the mysterious In-Context Learning (ICL) ability exhibited by Transformer architectures, especially in large language models (LLMs), has sparked significant research inte…
Adversarial Representation Engineering: A General Model Editing Framework for Large Language Models
Yihao Zhang, Zeming Wei, Jun Sun +1
Since the rapid development of Large Language Models (LLMs) has achieved remarkable success, understanding and rectifying their internal complex mechanisms has become an urgent iss…
On the Duality Between Sharpness-Aware Minimization and Adversarial Training
Yihao Zhang, Hangzhou He, Jingyu Zhu +3
Adversarial Training (AT), which adversarially perturb the input samples during training, has been acknowledged as one of the most effective defenses against adversarial attacks, y…
Fight Back Against Jailbreaking via Prompt Adversarial Tuning
Yichuan Mo, Yuji Wang, Zeming Wei +1
While Large Language Models (LLMs) have achieved tremendous success in various applications, they are also susceptible to jailbreaking attacks. Several primary defense strategies h…
Jatmo: Prompt Injection Defense by Task-Specific Finetuning
Julien Piet, Maha Alrashed, Chawin Sitawarin +5
Large Language Models (LLMs) are attracting significant research attention due to their instruction-following abilities, allowing users and developers to leverage LLMs for a variet…
Architecture Matters: Uncovering Implicit Mechanisms in Graph Contrastive Learning
Xiaojun Guo, Yifei Wang, Zeming Wei +1
With the prosperity of contrastive learning for visual representation learning (VCL), it is also adapted to the graph domain and yields promising performance. However, through a sy…