7 papers
Dynamic Optimization and Safety Indicator Injection for Jailbreaking Text-to-Image Models with Multimodal Safety Filters
Zixuan Chen, Hao Lin, Ke Xu +2
Text-to-image (T2I) models can generate not-safe-for-work (NSFW) content, motivating multi-stage safety pipelines with both text and image filters. Newer LLM-based filters detect l…
INHerit-SG: Incremental Hierarchical Semantic Scene Graphs with RAG-Style Retrieval
YukTungSamuel Fang, Zhikang Shi, Jiabin Qiu +5
Driven by recent advancements in foundation models, semantic scene graphs have emerged as a promising paradigm for high-level 3D environmental abstraction in robot navigation. Howe…
VideoAgent: Personalized Synthesis of Scientific Videos
Xiao Liang, Bangxin Li, Zixuan Chen +5
The technical complexity of research papers often limits their reach, necessitating more accessible formats like scientific videos to disseminate key insights through engaging narr…
Integrals and Rigidity on Manifolds with Nonnegative Ricci Curvature
Zixuan Chen, Guoyi Xu, Shuai Zhang
We prove the general sharp mean value inequality for non-negative superharmonic functions and its corresponding rigidity, which removes the radius restriction of Schoen-Yau's class…
LUMIR: an LLM-Driven Unified Agent Framework for Multi-task Infrared Spectroscopy Reasoning
Zujie Xie, Zixuan Chen, Jiheng Liang +2
Infrared spectroscopy enables rapid, non destructive analysis of chemical and material properties, yet high dimensional signals and overlapping bands hinder conventional chemometri…
Reactivation: Empirical NTK Dynamics Under Task Shifts
Yuzhi Liu, Zixuan Chen, Zirui Zhang +2
The Neural Tangent Kernel (NTK) offers a powerful tool to study the functional dynamics of neural networks. In the so-called lazy, or kernel regime, the NTK remains static during t…