5 papers
The Devil is in Attention Sharing: Improving Complex Non-rigid Image Editing Faithfulness via Attention Synergy
Zhuo Chen, Fanyue Wei, Runze Xu +4
Training-free image editing with large diffusion models has become practical, yet faithfully performing complex non-rigid edits (e.g., pose or shape changes) remains highly challen…
Dataset Distillation as Data Compression: A Rate-Utility Perspective
Youneng Bao, Yiping Liu, Zhuo Chen +3
Driven by the ``scale-is-everything'' paradigm, modern machine learning increasingly demands ever-larger datasets and models, yielding prohibitive computational and storage require…
Theoretical Insights in Model Inversion Robustness and Conditional Entropy Maximization for Collaborative Inference Systems
Song Xia, Yi Yu, Wenhan Yang +5
By locally encoding raw data into intermediate features, collaborative inference enables end users to leverage powerful deep learning models without exposure of sensitive raw data…
Injecting Universal Jailbreak Backdoors into LLMs in Minutes
Zhuowei Chen, Qiannan Zhang, Shichao Pei
Jailbreak backdoor attacks on LLMs have garnered attention for their effectiveness and stealth. However, existing methods rely on the crafting of poisoned datasets and the time-con…
Toward Scalable Image Feature Compression: A Content-Adaptive and Diffusion-Based Approach
Sha Guo, Zhuo Chen, Yang Zhao +3
Traditional image codecs emphasize signal fidelity and human perception, often at the expense of machine vision tasks. Deep learning methods have demonstrated promising coding perf…