37 citations · 51 across the 8 of their papers we have counts for
8 papers
Semantics as a Shield: Label Disguise Defense (LDD) against Prompt Injection in LLM Sentiment Classification
Yanxi Li, Ruocheng Shan
Prompt injection can cause large language models (LLMs) to deviate from their intended tasks by following instructions embedded in untrusted input. We investigate whether changing…
BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent
Zijian Chen, Xueguang Ma, Shengyao Zhuang +17
Deep-Research agents, which integrate large language models (LLMs) with search tools, have shown success in improving the effectiveness of handling complex queries that require ite…
Position: AI Scaling: From Up to Down and Out
Yunke Wang, Yanxi Li, Chang Xu
AI Scaling has traditionally been synonymous with Scaling Up, which builds larger and more powerful models. However, the growing demand for efficiency, adaptability, and collaborat…
Understanding Robustness of Visual State Space Models for Image Classification
Chengbin Du, Yanxi Li, Chang Xu
Visual State Space Model (VMamba) has recently emerged as a promising architecture, exhibiting remarkable performance in various computer vision tasks. However, its robustness has…
Neural Architecture Retrieval
Xiaohuan Pei, Yanxi Li, Minjing Dong +1
With the increasing number of new neural architecture designs and substantial existing neural architectures, it becomes difficult for the researchers to situate their contributions…
GPT Self-Supervision for a Better Data Annotator
Xiaohuan Pei, Yanxi Li, Chang Xu
The task of annotating data into concise summaries poses a significant challenge across various domains, frequently requiring the allocation of significant time and specialized kno…
Stable Diffusion is Unstable
Chengbin Du, Yanxi Li, Zhongwei Qiu +1
Recently, text-to-image models have been thriving. Despite their powerful generative capacity, our research has uncovered a lack of robustness in this generation process. Specifica…
Adversarially Robust Neural Architectures
Minjing Dong, Yanxi Li, Yunhe Wang +1
Deep Neural Networks (DNNs) are vulnerable to adversarial attacks. Existing methods are devoted to developing various robust training strategies or regularizations to update the we…