Superiority of Multi-Head Attention in In-Context Linear Regression von Cui, Yingqian, Ren, Jie, He, Pengfei, Tang, Jiliang, Xing, Yue

Volltext bestellen

A Theoretical Understanding of Chain-of-Thought: Coherent Reasoning and Error-Aware Demonstration von Cui, Yingqian, He, Pengfei, Tang, Xianfeng, He, Qi, Luo, Chen, Tang, Jiliang, Xing, Yue

Volltext bestellen

Towards the Effect of Examples on In-Context Learning: A Theoretical Case Study von He, Pengfei, Cui, Yingqian, Xu, Han, Liu, Hui, Yamada, Makoto, Tang, Jiliang, Xing, Yue

Volltext bestellen

Six-CD: Benchmarking Concept Removals for Benign Text-to-image Diffusion Models von Ren, Jie, Chen, Kangrui, Cui, Yingqian, Zeng, Shenglai, Liu, Hui, Xing, Yue, Tang, Jiliang, Lyu, Lingjuan

Volltext bestellen

EnTruth: Enhancing the Traceability of Unauthorized Dataset Usage in Text-to-image Diffusion Models with Minimal and Robust Alterations von Ren, Jie, Cui, Yingqian, Chen, Chen, Sehwag, Vikash, Xing, Yue, Tang, Jiliang, Lyu, Lingjuan

Volltext bestellen

A Robust Semantics-based Watermark for Large Language Model against Paraphrasing von Ren, Jie, Xu, Han, Liu, Yiding, Cui, Yingqian, Wang, Shuaiqiang, Yin, Dawei, Tang, Jiliang

Volltext bestellen

On the Generalization of Training-based ChatGPT Detection Methods von Xu, Han, Ren, Jie, He, Pengfei, Zeng, Shenglai, Cui, Yingqian, Liu, Amy, Liu, Hui, Tang, Jiliang

Volltext bestellen

DiffusionShield: A Watermark for Copyright Protection against Generative Diffusion Models von Cui, Yingqian, Ren, Jie, Xu, Han, He, Pengfei, Liu, Hui, Sun, Lichao, Xing, Yue, Tang, Jiliang

Volltext bestellen

Sharpness-Aware Data Poisoning Attack von He, Pengfei, Xu, Han, Ren, Jie, Cui, Yingqian, Liu, Hui, Aggarwal, Charu C, Tang, Jiliang

Volltext bestellen

Stealthy Backdoor Attack via Confidence-driven Sampling von He, Pengfei, Xing, Yue, Xu, Han, Ren, Jie, Cui, Yingqian, Zeng, Shenglai, Tang, Jiliang, Yamada, Makoto, Sabokrou, Mohammad

Volltext bestellen

FT-Shield: A Watermark Against Unauthorized Fine-tuning in Text-to-Image Diffusion Models von Cui, Yingqian, Ren, Jie, Lin, Yuping, Xu, Han, He, Pengfei, Xing, Yue, Lyu, Lingjuan, Fan, Wenqi, Liu, Hui, Tang, Jiliang

Volltext bestellen

Copyright Protection in Generative AI: A Technical Perspective von Ren, Jie, Xu, Han, He, Pengfei, Cui, Yingqian, Zeng, Shenglai, Zhang, Jiankun, Wen, Hongzhi, Ding, Jiayuan, Huang, Pei, Lyu, Lingjuan, Liu, Hui, Chang, Yi, Tang, Jiliang

Volltext bestellen

Superiority of Multi-Head Attention in In-Context Linear Regression von Cui, Yingqian, Ren, Jie, He, Pengfei, Tang, Jiliang, Xing, Yue

Volltext

A Theoretical Understanding of Chain-of-Thought: Coherent Reasoning and Error-Aware Demonstration von Cui, Yingqian, He, Pengfei, Tang, Xianfeng, He, Qi, Chen, Luo, Tang, Jiliang, Xing, Yue

Volltext

Towards the Effect of Examples on In-Context Learning: A Theoretical Case Study von He, Pengfei, Cui, Yingqian, Xu, Han, Liu, Hui, Yamada, Makoto, Tang, Jiliang, Xing, Yue

Volltext

Six-CD: Benchmarking Concept Removals for Benign Text-to-image Diffusion Models von Ren, Jie, Chen, Kangrui, Cui, Yingqian, Zeng, Shenglai, Liu, Hui, Xing, Yue, Tang, Jiliang, Lyu, Lingjuan

Volltext

EnTruth: Enhancing the Traceability of Unauthorized Dataset Usage in Text-to-image Diffusion Models with Minimal and Robust Alterations von Ren, Jie, Cui, Yingqian, Chen, Chen, Sehwag, Vikash, Xing, Yue, Tang, Jiliang, Lyu, Lingjuan

Volltext

DiffusionShield: A Watermark for Copyright Protection against Generative Diffusion Models von Cui, Yingqian, Ren, Jie, Xu, Han, He, Pengfei, Liu, Hui, Sun, Lichao, Xing, Yue, Tang, Jiliang

Volltext

Sharpness-Aware Data Poisoning Attack von He, Pengfei, Xu, Han, Ren, Jie, Cui, Yingqian, Liu, Hui, Aggarwal, Charu C, Tang, Jiliang

Volltext

A Robust Semantics-based Watermark for Large Language Model against Paraphrasing von Ren, Jie, Xu, Han, Liu, Yiding, Cui, Yingqian, Wang, Shuaiqiang, Yin, Dawei, Tang, Jiliang

Volltext