1 citations · 1 across the 9 of their papers we have counts for
9 papers
Quantum Incremental Learning with Mixed State Prototypes
Yu Wu, Qianli Zhou, Xinyang Deng +3
Incremental learning models are required to learn new classes sequentially without catastrophic forgetting, while operating under parameter and memory constraints. In the Noisy Int…
DOW-KE: Anchor-Free Multi-Layer Knowledge Editing via Direct End-to-End Weight Optimization
Ran Chen, Junbo Zhang, Qianli Zhou +2
Multi-layer locate-then-edit methods for knowledge editing first optimize target residual-stream activations (anchors) at selected layers, then realize them layer by layer as weigh…
DataRx: Missingness-Aware Sampling for Safer Large Language Model Task-Specific Fine-Tuning
Junbo Zhang, Qianli Zhou, Xinyang Deng +1
Task-specific fine-tuning can improve the performance of large language models (LLMs) on downstream tasks. However, our study reveals that task-specific fine-tuning can also weaken…
DataShield: Safety-degrading Data Filtering for LLM Benign Instruction Fine-Tuning
Junbo Zhang, Qianli Zhou, Xinyang Deng +3
Large language models (LLMs) suffer from degraded safety capabilities even when fine-tuned with benign datasets. However, existing methods for identifying safety-degrading samples…
A Unified and Reproducible Experimentation Framework for Speech Understanding
Jing Peng, Junhao Du, Chenghao Wang +21
Speech foundation models and Speech LLMs have advanced speech understanding, yet deployment-oriented model selection is hindered by non-comparable evaluations caused by mismatched…
Feature Entanglement-based Quantum Multimodal Fusion Neural Network
Yu Wu, Qianli Zhou, Jie Geng +2
Multimodal learning aims to enhance perceptual and decision-making capabilities by integrating information from diverse sources. However, classical deep learning approaches face a…
Understanding and Mitigating Over-refusal for Large Language Models via Representation Intervention
Junbo Zhang, Ran Chen, Qianli Zhou +2
Large language models (LLMs) demonstrate powerful capabilities across various natural language processing tasks,yet their inherent safety vulnerabilities undermine the reliable app…
Sample-agnostic Adversarial Perturbation for Vision-Language Pre-training Models
Haonan Zheng, Wen Jiang, Xinyang Deng +1
Recent studies on AI security have highlighted the vulnerability of Vision-Language Pre-training (VLP) models to subtle yet intentionally designed perturbations in images and texts…
A Unified Understanding of Adversarial Vulnerability Regarding Unimodal Models and Vision-Language Pre-training Models
Haonan Zheng, Xinyang Deng, Wen Jiang +1
With Vision-Language Pre-training (VLP) models demonstrating powerful multimodal interaction capabilities, the application scenarios of neural networks are no longer confined to un…