9 papers
Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety
Ping Wu, Haibo Tong, Feifei Zhao +7
Safety tuning can improve harmful refusal, but models may learn surface-form shortcuts: wrapped harmful prompts bypass safety, while similarly wrapped benign prompts are over-refus…
Spiking Local Interaction and Adaptive Complementary Fusion for Spiking Transformer
Dongcheng Zhao, Sicheng Shen, Zhenyu Yang +6
Spiking Transformers model token interactions primarily through spiking self-attention (SSA). However, binary query and key representations map continuous similarities to sparse an…
ForesightSafety-VLA: A Unified Diagnostic Safety Benchmark for Vision-Language-Action Models
Mingyang Lyu, Yinqian Sun, Yiyang Jia +5
In embodied intelligence, safety is a prerequisite for reliable robot deployment in the physical world. Current vision-language-action (VLA) models continue to advance toward gener…
SciRisk-Bench: A Risk-Dimension-Aware Benchmark for AI4Science Safety
Linghao Feng, Yinqian Sun, Dongqi Liang +8
Large language models (LLMs) are increasingly embedded in AI for Science (AI4Science) workflows, from scientific question answering and literature analysis to laboratory planning a…
Light Alignment Improves LLM Safety via Model Self-Reflection with a Single Neuron
Sicheng Shen, Mingyang Lv, Han Shen +7
The safety of large language models (LLMs) has increasingly emerged as a fundamental aspect of their development. Existing safety alignment for LLMs is predominantly achieved throu…
TEFormer: Structured Bidirectional Temporal Enhancement Modeling in Spiking Transformers
Sicheng Shen, Mingyang Lv, Bing Han +4
In recent years, Spiking Neural Networks (SNNs) have achieved remarkable progress, with Spiking Transformers emerging as a promising architecture for energy-efficient sequence mode…