1 citations · 1 across the 4 of their papers we have counts for
5 papers
Attention Sees, MLP Refuses: Tracing the Attention-to-MLP Safety Pathway in LLMs
Zixuan Weng, Haoqi He, Weifei Jin +2
Safety-aligned large language models (LLMs) remain vulnerable to jailbreaks and can over-refuse benign requests. Understanding these failures requires distinguishing harmfulness re…
FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models
Zixuan Weng, Jinghuai Zhang, Kunlin Cai +3
Large language models (LLMs) often exhibit undesirable behaviors, such as safety violations and hallucinations. Although inference-time steering offers a cost-effective way to adju…
DAMBench: A Multi-Modal Benchmark for Deep Learning-based Atmospheric Data Assimilation
Hao Wang, Zixuan Weng, Jindong Han +2
Data Assimilation is a cornerstone of atmospheric system modeling, tasked with reconstructing system states by integrating sparse, noisy observations with prior estimation. While t…
Foot-In-The-Door: A Multi-turn Jailbreak for LLMs
Zixuan Weng, Xiaolong Jin, Jinyuan Jia +1
Ensuring AI safety is crucial as large language models become increasingly integrated into real-world applications. A key challenge is jailbreak, where adversarial prompts bypass b…
SDE: A Simplified and Disentangled Dependency Encoding Framework for State Space Models in Time Series Forecasting
Zixuan Weng, Jindong Han, Wenzhao Jiang +1
In recent years, advancements in deep learning have spurred the development of numerous models for Long-term Time Series Forecasting (LTSF). However, most existing approaches strug…