Search Results for author: Xiang He

Found 22 papers, 4 papers with code

Harnessing Task Overload for Scalable Jailbreak Attacks on Large Language Models

no code implementations5 Oct 2024 Yiting Dong, Guobin Shen, Dongcheng Zhao, Xiang He, Yi Zeng

Existing attack methods are fixed or specifically tailored for certain models and cannot flexibly adjust attack strength, which is critical for generalization when attacking models of various sizes.

Prompt Engineering

Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models

no code implementations3 Oct 2024 Guobin Shen, Dongcheng Zhao, Yiting Dong, Xiang He, Yi Zeng

In this paper, we introduce Jailbreak Antidote, a method that enables real-time adjustment of LLM safety preferences by manipulating a sparse subset of the model's internal states during inference.

Prompt Engineering

Local Search for Integer Quadratic Programming

no code implementations29 Sep 2024 Xiang He, Peng Lin, Shaowei Cai

Local search is a powerful method for solving hard problems, but the research on local search algorithms for IQP solving is still on its early stage.

StressPrompt: Does Stress Impact Large Language Models and Human Performance Similarly?

no code implementations14 Sep 2024 Guobin Shen, Dongcheng Zhao, Aorigele Bao, Xiang He, Yiting Dong, Yi Zeng

Moreover, this study contributes to the broader AI research community by offering a new perspective on how LLMs handle different scenarios and their similarities to human cognition.

Emotional Intelligence Instruction Following

CACE-Net: Co-guidance Attention and Contrastive Enhancement for Effective Audio-Visual Event Localization

1 code implementation4 Aug 2024 Xiang He, Xiangxi Liu, Yang Li, Dongcheng Zhao, Guobin Shen, Qingqun Kong, Xin Yang, Yi Zeng

Specifically, we have enhanced the model's ability to discern subtle differences between event and background and improved the accuracy of event classification in our model.

audio-visual event localization

Spiking Neural Networks with Consistent Mapping Relations Allow High-Accuracy Inference

no code implementations8 Jun 2024 Yang Li, Xiang He, Qingqun Kong, Yi Zeng

Spike-based neuromorphic hardware has demonstrated substantial potential in low energy consumption and efficient inference.

object-detection Object Detection

Neuro-Vision to Language: Enhancing Brain Recording-based Visual Reconstruction and Language Interaction

no code implementations30 Apr 2024 Guobin Shen, Dongcheng Zhao, Xiang He, Linghao Feng, Yiting Dong, Jihang Wang, Qian Zhang, Yi Zeng

Decoding non-invasive brain recordings is pivotal for advancing our understanding of human cognition but faces challenges due to individual differences and complex neural signal representations.

Brain Decoding Image Reconstruction +1

Light-weight Retinal Layer Segmentation with Global Reasoning

1 code implementation25 Apr 2024 Xiang He, Weiye Song, Yiming Wang, Fabio Poiesi, Ji Yi, Manishi Desai, Quanqing Xu, Kongzheng Yang, Yi Wan

Automatic retinal layer segmentation with medical images, such as optical coherence tomography (OCT) images, serves as an important tool for diagnosing ophthalmic diseases.

Decoder Segmentation

SA-GS: Scale-Adaptive Gaussian Splatting for Training-Free Anti-Aliasing

1 code implementation28 Mar 2024 Xiaowei Song, Jv Zheng, Shiran Yuan, Huan-ang Gao, Jingwei Zhao, Xiang He, Weihao Gu, Hao Zhao

This integration is actually a limiting case of super-sampling, which significantly improves anti-aliasing performance over vanilla Gaussian Splatting.

A Survey on Deep Neural Network Partition over Cloud, Edge and End Devices

no code implementations20 Apr 2023 Di Xu, Xiang He, Tonghua Su, Zhongjie Wang

This paper provides a comprehensive survey on the recent advances and challenges in DNN partition approaches over the cloud, edge, and end devices based on a detailed literature collection.

Edge-computing

MSAT: Biologically Inspired Multi-Stage Adaptive Threshold for Conversion of Spiking Neural Networks

no code implementations23 Mar 2023 Xiang He, Yang Li, Dongcheng Zhao, Qingqun Kong, Yi Zeng

The self-adaptation to membrane potential and input allows a timely adjustment of the threshold to fire spike faster and transmit more information.

Sentiment Analysis Sentiment Classification +2

An Efficient Knowledge Transfer Strategy for Spiking Neural Networks from Static to Event Domain

1 code implementation23 Mar 2023 Xiang He, Dongcheng Zhao, Yang Li, Guobin Shen, Qingqun Kong, Yi Zeng

In order to improve the generalization ability of SNNs on event-based datasets, we use static images to assist SNN training on event data.

Transfer Learning

Spike Calibration: Fast and Accurate Conversion of Spiking Neural Network for Object Detection and Segmentation

no code implementations6 Jul 2022 Yang Li, Xiang He, Yiting Dong, Qingqun Kong, Yi Zeng

Spiking neural network (SNN) has been attached to great importance due to the properties of high biological plausibility and low energy consumption on neuromorphic hardware.

Bayesian Optimization object-detection +1

Magic Pyramid: Accelerating Inference with Early Exiting and Token Pruning

no code implementations30 Oct 2021 Xuanli He, Iman Keivanloo, Yi Xu, Xiang He, Belinda Zeng, Santosh Rajagopalan, Trishul Chilimbi

To achieve this, we propose a novel idea, Magic Pyramid (MP), to reduce both width-wise and depth-wise computation via token pruning and early exiting for Transformer-based models, particularly BERT.

text-classification Text Classification

PAM: Understanding Product Images in Cross Product Category Attribute Extraction

no code implementations8 Jun 2021 Rongmei Lin, Xiang He, Jie Feng, Nasser Zalmout, Yan Liang, Li Xiong, Xin Luna Dong

Understanding product attributes plays an important role in improving online shopping experience for customers and serves as an integral part for constructing a product knowledge graph.

Attribute Attribute Extraction +4

Non-Local Context Encoder: Robust Biomedical Image Segmentation against Adversarial Attacks

no code implementations27 Apr 2019 Xiang He, Sibei Yang, Guanbin Li?, Haofeng Li, Huiyou Chang, Yizhou Yu

In this paper, we discover that global spatial dependencies and global contextual information in a biomedical image can be exploited to defend against adversarial attacks.

Image Segmentation Lesion Segmentation +3

Non-locally Enhanced Encoder-Decoder Network for Single Image De-raining

no code implementations4 Aug 2018 Guanbin Li, Xiang He, Wei zhang, Huiyou Chang, Le Dong, Liang Lin

Single image rain streaks removal has recently witnessed substantial progress due to the development of deep convolutional neural networks.

Decoder

Cannot find the paper you are looking for? You can Submit a new open access paper.