Yi Zeng

18

Papers

186

Total Citations

Papers (18)

SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

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

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

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

Towards High-Resolution Salient Object Detection

Rethinking the Backdoor Attacks' Triggers: A Frequency Perspective

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

Are Conventional SNNs Really Efficient? A Perspective from Network Quantization

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

MatchDet: A Collaborative Framework for Image Matching and Object Detection

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

RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content

Position: A Safe Harbor for AI Evaluation and Red Teaming

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

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

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