Multi-Modal Recommendation Unlearning for Legal, Licensing, and Modality Constraintsby Yash Sinha, Murari Mandal, Mohan KankanhalliFirst…
Cross-Validated Off-Policy Evaluationby Matej Cief, Branislav Kveton, Michal KompanFirst submitted to arxiv on: 24 May…
Discriminative Estimation of Total Variation Distance: A Fidelity Auditor for Generative Databy Lan Tao, Shirong…
BiSup: Bidirectional Quantization Error Suppression for Large Language Modelsby Minghui Zou, Ronghui Guo, Sai Zhang,…
Strong screening rules for group-based SLOPE modelsby Fabio Feser, Marina EvangelouFirst submitted to arxiv on:…
Coordinated Multi-Neighborhood Learning on a Directed Acyclic Graphby Stephen Smith, Qing ZhouFirst submitted to arxiv…
Cross-Domain Policy Adaptation by Capturing Representation Mismatchby Jiafei Lyu, Chenjia Bai, Jingwen Yang, Zongqing Lu,…
Log-Concave Sampling on Compact Supports: A Versatile Proximal Frameworkby Lu YuFirst submitted to arxiv on:…
Pipeline Parallelism with Controllable Memoryby Penghui Qi, Xinyi Wan, Nyamdavaa Amar, Min LinFirst submitted to…
Efficient Recurrent Off-Policy RL Requires a Context-Encoder-Specific Learning Rateby Fan-Ming Luo, Zuolin Tu, Zefang Huang,…