Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMsby Ling Yang, Zhaochen Yu, Chenlin…
Multi-level Cross-modal Alignment for Image Clusteringby Liping Qiu, Qin Zhang, Xiaojun Chen, Shaotian CaiFirst submitted…
Projected Belief Networks With Discriminative Alignment for Acoustic Event Classification: Rivaling State of the Art…
Starlit: Privacy-Preserving Federated Learning to Enhance Financial Fraud Detectionby Aydin Abadi, Bradley Doyle, Francesco Gini,…
Early alignment in two-layer networks training is a two-edged swordby Etienne Boursier, Nicolas FlammarionFirst submitted…
Improving automatic detection of driver fatigue and distraction using machine learningby Dongjiang WuFirst submitted to…
Improving fine-grained understanding in image-text pre-trainingby Ioana Bica, Anastasija Ilić, Matthias Bauer, Goker Erdogan, Matko…
Residual Alignment: Uncovering the Mechanisms of Residual Networksby Jianing Li, Vardan PapyanFirst submitted to arxiv…
FedLoGe: Joint Local and Generic Federated Learning under Long-tailed Databy Zikai Xiao, Zihan Chen, Liyinglan…
Adversarial Supervision Makes Layout-to-Image Diffusion Models Thriveby Yumeng Li, Margret Keuper, Dan Zhang, Anna KhorevaFirst…