ICLR 2025 "generative models" Papers
17 papers found
Adding Conditional Control to Diffusion Models with Reinforcement Learning
Yulai Zhao, Masatoshi Uehara, Gabriele Scalia et al.
Adjoint Matching: Fine-tuning Flow and Diffusion Generative Models with Memoryless Stochastic Optimal Control
Carles Domingo i Enrich, Michal Drozdzal, Brian Karrer et al.
Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models Trained on Corrupted Data
Asad Aali, Giannis Daras, Brett Levac et al.
Bayesian Experimental Design Via Contrastive Diffusions
Jacopo Iollo, Christophe Heinkelé, Pierre Alliez et al.
Diffusion Transformers for Tabular Data Time Series Generation
Fabrizio Garuti, Enver Sangineto, Simone Luetto et al.
Faster Inference of Flow-Based Generative Models via Improved Data-Noise Coupling
Aram Davtyan, Leello Dadi, Volkan Cevher et al.
From Search to Sampling: Generative Models for Robust Algorithmic Recourse
Prateek Garg, Lokesh Nagalapatti, Sunita Sarawagi
GMValuator: Similarity-based Data Valuation for Generative Models
Jiaxi Yang, Wenlong Deng, Benlin Liu et al.
InCoDe: Interpretable Compressed Descriptions For Image Generation
Armand Comas, Aditya Chattopadhyay, Feliu Formosa et al.
Learning to Discretize Denoising Diffusion ODEs
Vinh Tong, Trung-Dung Hoang, Anji Liu et al.
Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better
Enshu Liu, Junyi Zhu, Zinan Lin et al.
One Step Diffusion via Shortcut Models
Kevin Frans, Danijar Hafner, Sergey Levine et al.
PRISM: Privacy-Preserving Improved Stochastic Masking for Federated Generative Models
Kyeongkook Seo, Dong-Jun Han, Jaejun Yoo
ProtoSnap: Prototype Alignment For Cuneiform Signs
Rachel Mikulinsky, Morris Alper, Shai Gordin et al.
RTDiff: Reverse Trajectory Synthesis via Diffusion for Offline Reinforcement Learning
Qianlan Yang, Yu-Xiong Wang
Stiefel Flow Matching for Moment-Constrained Structure Elucidation
Austin H Cheng, Alston Lo, Kin Long Kelvin Lee et al.
SynFlowNet: Design of Diverse and Novel Molecules with Synthesis Constraints
Miruna Cretu, Charles Harris, Ilia Igashov et al.