Risultati della ricerca - Lin, Huawei

DMin: Scalable Training Data Influence Estimation for Diffusion Models di Lin, Huawei, Lao, Yingjie, Zhao, Weijie

Testo

RapidUn: Influence-Driven Parameter Reweighting for Efficient Large Language Model Unlearning di Zhao, Guoshenghui, Lin, Huawei, Zhao, Weijie

Testo

Token-wise Influential Training Data Retrieval for Large Language Models di Lin, Huawei, Long, Jikai, Xu, Zhaozhuo, Zhao, Weijie

Testo

VTBench: Evaluating Visual Tokenizers for Autoregressive Image Generation di Lin, Huawei, Geng, Tong, Xu, Zhaozhuo, Zhao, Weijie

Testo

Online Gradient Boosting Decision Tree: In-Place Updates for Efficient Adding/Deleting Data di Lin, Huawei, Chung, Jun Woo, Lao, Yingjie, Zhao, Weijie

Testo

UniGuardian: A Unified Defense for Detecting Prompt Injection, Backdoor Attacks and Adversarial Attacks in Large Language Models di Lin, Huawei, Lao, Yingjie, Geng, Tong, Yu, Tan, Zhao, Weijie

Testo

MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation di Lin, Huawei, Li, Peng, Song, Jie, Jiang, Fuxin, Zhang, Tieying

Testo

Agent-Omni: Test-Time Multimodal Reasoning via Model Coordination for Understanding Anything di Lin, Huawei, Shi, Yunzhi, Geng, Tong, Zhao, Weijie, Wang, Wei, Singh, Ravender Pal

Testo

ALinFiK: Learning to Approximate Linearized Future Influence Kernel for Scalable Third-Party LLM Data Valuation di Pan, Yanzhou, Lin, Huawei, Ran, Yide, Chen, Jiamin, Yu, Xiaodong, Zhao, Weijie, Zhang, Denghui, Xu, Zhaozhuo

Testo

Randomized Antipodal Search Done Right for Data Pareto Improvement of LLM Unlearning di Liu, Ziwen, Lin, Huawei, Ran, Yide, Zhang, Denghui, Xie, Jianwen, Li, Chuan, Zhao, Weijie, Xu, Zhaozhuo

Testo

DebiasRAG: A Tuning-Free Path to Fair Generation in Large Language Models through Retrieval-Augmented Generation di Chu, Rui, Zhao, Bingyin, Le, Thanh Quoc Hung, Hoang, Duy Cao, Lin, Huawei, Li, Ping, Zhao, Weijie, Doan, Khoa D, Lao, Yingjie

Testo