HERO: Human-Feedback Efficient Reinforcement Learning for Online Diffusion Model Finetuningby Ayano Hiranaka, Shang-Fu Chen, Chieh-Hsin…
LOTOS: Layer-wise Orthogonalization for Training Robust Ensemblesby Ali Ebrahimpour-Boroojeny, Hari Sundaram, Varun ChandrasekaranFirst submitted to…
A Simulation-Free Deep Learning Approach to Stochastic Optimal Controlby Mengjian Hua, Matthieu Laurière, Eric Vanden-EijndenFirst…
Double Oracle Neural Architecture Search for Game Theoretic Deep Learning Modelsby Aye Phyu Phyu Aung,…
Granular Ball Twin Support Vector Machineby A. Quadir, M. Sajid, M. TanveerFirst submitted to arxiv…
Improving Image Clustering with Artifacts Attenuation via Inference-Time Attention Engineeringby Kazumoto Nakamura, Yuji Nozawa, Yu-Chieh…
Building Damage Assessment in Conflict Zones: A Deep Learning Approach Using Geospatial Sub-Meter Resolution Databy…
Timer-XL: Long-Context Transformers for Unified Time Series Forecastingby Yong Liu, Guo Qin, Xiangdong Huang, Jianmin…
Learning Interpretable Hierarchical Dynamical Systems Models from Time Series Databy Manuel Brenner, Elias Weber, Georgia…
FedBiP: Heterogeneous One-Shot Federated Learning with Personalized Latent Diffusion Modelsby Haokun Chen, Hang Li, Yao…