3 citations · 4 across the 9 of their papers we have counts for
12 papers
Rethinking Pairwise Token Interaction in Spiking Transformers
Sicheng Shen, Dongcheng Zhao, Zhiyuan Li +5
Spiking Transformers inherit token interaction mechanisms from conventional Transformers, yet their sparse binary representations fundamentally alter how token-to-token communicati…
Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety
Ping Wu, Haibo Tong, Feifei Zhao +7
A common way to improve jailbreak robustness is to train on harmful requests rewritten as role-play, translation, or other forms. When used only for harmful requests, these forms m…
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…
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks
Guobin Shen, Dongcheng Zhao, Linghao Feng +8
Large language models (LLMs) have achieved remarkable capabilities but remain vulnerable to adversarial prompts known as jailbreaks, which can bypass safety alignment and elicit ha…
STEP: A Unified Spiking Transformer Evaluation Platform for Fair and Reproducible Benchmarking
Sicheng Shen, Dongcheng Zhao, Linghao Feng +5
Spiking Transformers have recently emerged as promising architectures for combining the efficiency of spiking neural networks with the representational power of self-attention. How…
Biologically Inspired Spiking Diffusion Model with Adaptive Lateral Selection Mechanism
Linghao Feng, Dongcheng Zhao, Sicheng Shen +1
Lateral connection is a fundamental feature of biological neural circuits, facilitating local information processing and adaptive learning. In this work, we integrate lateral conne…
Time Cell Inspired Temporal Codebook in Spiking Neural Networks for Enhanced Image Generation
Linghao Feng, Dongcheng Zhao, Sicheng Shen +3
This paper presents a novel approach leveraging Spiking Neural Networks (SNNs) to construct a Variational Quantized Autoencoder (VQ-VAE) with a temporal codebook inspired by hippoc…
TIM: An Efficient Temporal Interaction Module for Spiking Transformer
Sicheng Shen, Dongcheng Zhao, Guobin Shen +1
Spiking Neural Networks (SNNs), as the third generation of neural networks, have gained prominence for their biological plausibility and computational efficiency, especially in pro…