Yi Zeng

papers

707

total citations

papers (20)

Rethinking the Backdoor Attacks' Triggers: A Frequency Perspective

ICCV 2021arXiv

255

citations

SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

ICLR 2025arXiv

151

citations

CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks

NEURIPS 2022arXiv

citations

RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content

ICML 2024arXiv

citations

BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices

CVPR 2025arXiv

citations

tSF: Transformer-Based Semantic Filter for Few-Shot Learning

ECCV 2022arXiv

citations

Bullying10K: A Large-Scale Neuromorphic Dataset towards Privacy-Preserving Bullying Recognition

NEURIPS 2023arXiv

citations

AutoRedTeamer: Autonomous Red Teaming with Lifelong Attack Integration

NEURIPS 2025arXiv

citations

AIR-BENCH 2024: A Safety Benchmark based on Regulation and Policies Specified Risk Categories

ICLR 2025

citations

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

ICLR 2025arXiv

citations

Learning Task-Aware Language-Image Representation for Class-Incremental Object Detection

AAAI 2024

citations

MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models

ICLR 2025arXiv

citations

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

AAAI 2024arXiv

citations

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

AAAI 2025arXiv

citations

SpikePack: Enhanced Information Flow in Spiking Neural Networks with High Hardware Compatibility

ICCV 2025arXiv

citations

EventZoom: A Progressive Approach to Event-Based Data Augmentation for Enhanced Neuromorphic Vision

AAAI 2025arXiv

citations

Yi Zeng

papers (20)

Rethinking the Backdoor Attacks' Triggers: A Frequency Perspective

SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks

RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content

BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices

tSF: Transformer-Based Semantic Filter for Few-Shot Learning

Bullying10K: A Large-Scale Neuromorphic Dataset towards Privacy-Preserving Bullying Recognition

AutoRedTeamer: Autonomous Red Teaming with Lifelong Attack Integration

AIR-BENCH 2024: A Safety Benchmark based on Regulation and Policies Specified Risk Categories

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

Learning Task-Aware Language-Image Representation for Class-Incremental Object Detection

MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models

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

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

SpikePack: Enhanced Information Flow in Spiking Neural Networks with High Hardware Compatibility

EventZoom: A Progressive Approach to Event-Based Data Augmentation for Enhanced Neuromorphic Vision

MatchDet: A Collaborative Framework for Image Matching and Object Detection

Where Did I Come From? Origin Attribution of AI-Generated Images

Position: A Safe Harbor for AI Evaluation and Red Teaming

Are Conventional SNNs Really Efficient? A Perspective from Network Quantization

papers (20)

Rethinking the Backdoor Attacks' Triggers: A Frequency Perspective

SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks

RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content

BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices

tSF: Transformer-Based Semantic Filter for Few-Shot Learning

Bullying10K: A Large-Scale Neuromorphic Dataset towards Privacy-Preserving Bullying Recognition

AutoRedTeamer: Autonomous Red Teaming with Lifelong Attack Integration

AIR-BENCH 2024: A Safety Benchmark based on Regulation and Policies Specified Risk Categories

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

Learning Task-Aware Language-Image Representation for Class-Incremental Object Detection

MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models

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

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

SpikePack: Enhanced Information Flow in Spiking Neural Networks with High Hardware Compatibility

EventZoom: A Progressive Approach to Event-Based Data Augmentation for Enhanced Neuromorphic Vision

MatchDet: A Collaborative Framework for Image Matching and Object Detection

Where Did I Come From? Origin Attribution of AI-Generated Images

Position: A Safe Harbor for AI Evaluation and Red Teaming

Are Conventional SNNs Really Efficient? A Perspective from Network Quantization