View-Invariant Pixelwise Anomaly Detection in Multi-object Scenes with Adaptive View Synthesisby Subin Varghese, Vedhus HoskereFirst…
EvolvED: Evolutionary Embeddings to Understand the Generation Process of Diffusion Modelsby Vidya Prasad, Hans van…
Aligning Diffusion Models with Noise-Conditioned Perceptionby Alexander Gambashidze, Anton Kulikov, Yuriy Sosnin, Ilya MakarovFirst submitted…
BMIKE-53: Investigating Cross-Lingual Knowledge Editing with In-Context Learningby Ercong Nie, Bo Shao, Zifeng Ding, Mingyang…
Towards Comprehensive Preference Data Collection for Reward Modelingby Yulan Hu, Qingyang Li, Sheng Ouyang, Ge…
Vision-Language Consistency Guided Multi-modal Prompt Learning for Blind AI Generated Image Quality Assessmentby Jun Fu,…
Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Mergingby Deyuan Liu, Zhanyue Qin,…
Prompt-Consistency Image Generation (PCIG): A Unified Framework Integrating LLMs, Knowledge Graphs, and Controllable Diffusion Modelsby…
Code-Switching Red-Teaming: LLM Evaluation for Safety and Multilingual Understandingby Haneul Yoo, Yongjin Yang, Hwaran LeeFirst…
PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preferenceby Jiaming Ji, Donghai Hong, Borong…