HSTFL: A Heterogeneous Federated Learning Framework for Misaligned Spatiotemporal Forecastingby Shuowei Cai, Hao LiuFirst submitted…
Multi-View and Multi-Scale Alignment for Contrastive Language-Image Pre-training in Mammographyby Yuexi Du, John Onofrey, Nicha…
Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior Modelsby Hui-Po Wang,…
MIO: A Foundation Model on Multimodal Tokensby Zekun Wang, King Zhu, Chunpu Xu, Wangchunshu Zhou,…
Modulated Intervention Preference Optimization (MIPO): Keep the Easy, Refine the Difficultby Cheolhun JangFirst submitted to…
A Simple but Strong Baseline for Sounding Video Generation: Effective Adaptation of Audio and Video…
Pixel-Space Post-Training of Latent Diffusion Modelsby Christina Zhang, Simran Motwani, Matthew Yu, Ji Hou, Felix…
Exploring Information-Theoretic Metrics Associated with Neural Collapse in Supervised Trainingby Kun Song, Zhiquan Tan, Bochao…
Source-Free Domain Adaptation for YOLO Object Detectionby Simon Varailhon, Masih Aminbeidokhti, Marco Pedersoli, Eric GrangerFirst…
AlignedKV: Reducing Memory Access of KV-Cache with Precision-Aligned Quantizationby Yifan Tan, Haoze Wang, Chao Yan,…