作者位次 #4/4ICLR 2026Poster· Social Aspects / Privacy-preserving Statistics and Machine Learning
DP-Fusion: Token-Level Differentially Private Inference for Large Language Models
Rushil Thareja · Preslav Nakov · Praneeth Vepakomma · Nils Lukas
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Rushil Thareja · Preslav Nakov · Praneeth Vepakomma · Nils Lukas
Fahad Shamshad · Nils Lukas · Karthik Nandakumar
Yubo Wang · Juntian Zhang · Yichen WU · Yankai Lin · Nils Lukas · Yuhan Liu
While Chain-of-Thought empowers Large Vision-Language Models with multi-step reasoning, explicit textual rationales suffer from an information bandwidth bottleneck, where continuous visual details are discarded during discrete tokenization. Recent latent reasoning methods attempt to address this...
Dylan Xinming Hou · Juntian Zhang · Xu Gu · Yichen WU · Nils Lukas · Gus Xia · Xiuying Chen · Yuhan Liu
The evolving realism of AI-generated Videos (AIGC-V) is rapidly rendering traditional artifact-centric detection insufficient, necessitating a paradigm shift from low-level inspection to high-level semantic verification. This paper presents a comprehensive survey of AIGC-V detection, reframing th...