Jonas Kohler

28 papers A* 7A 2Journal 18
YearRankTypeTitle / Venue / Authors
2025 A* conf
Adaptive Guidance: Training-free Acceleration of Conditional Diffusion Models.
AAAI
Angela Castillo, Jonas Kohler, Juan C. Pérez, Juan Pablo Pérez, Albert Pumarola, Bernard Ghanem, Pablo Arbeláez, Ali K. Thabet
2025 A* conf
Autoregressive Distillation of Diffusion Transformers.
CVPR
Yeongmin Kim, Sotiris Anagnostidis, Yuming Du, Edgar Schönfeld, Jonas Kohler, Markos Georgopoulos, Albert Pumarola, Ali K. Thabet, Artsiom Sanakoyeu
2025 J jnl
Autoregressive Distillation of Diffusion Transformers.
CoRR
Yeongmin Kim, Sotiris Anagnostidis, Yuming Du, Edgar Schönfeld, Jonas Kohler, Markos Georgopoulos, Albert Pumarola, Ali K. Thabet, Artsiom Sanakoyeu
2025 A* conf
FlexiDiT: Your Diffusion Transformer Can Easily Generate High-Quality Samples with Less Compute.
CVPR
Sotiris Anagnostidis, Gregor Bachmann, Yeongmin Kim, Jonas Kohler, Markos Georgopoulos, Artsiom Sanakoyeu, Yuming Du, Albert Pumarola, Ali K. Thabet, Edgar Schönfeld
2025 J jnl
FlexiDiT: Your Diffusion Transformer Can Easily Generate High-Quality Samples with Less Compute.
CoRR
Sotiris Anagnostidis, Gregor Bachmann, Yeongmin Kim, Jonas Kohler, Markos Georgopoulos, Artsiom Sanakoyeu, Yuming Du, Albert Pumarola, Ali K. Thabet, Edgar Schönfeld
2025 A* conf
Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment.
ICLR
Gregor Bachmann, Sotiris Anagnostidis, Albert Pumarola, Markos Georgopoulos, Artsiom Sanakoyeu, Yuming Du, Edgar Schönfeld, Ali K. Thabet, Jonas Kohler
2025 J jnl
Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment.
CoRR
Gregor Bachmann, Sotiris Anagnostidis, Albert Pumarola, Markos Georgopoulos, Artsiom Sanakoyeu, Yuming Du, Edgar Schönfeld, Ali K. Thabet, Jonas Kohler
2025 A* conf
Storybooth: Training-Free Multi-Subject Consistency for Improved Visual Storytelling.
ICLR
Jaskirat Singh, Junshen K. Chen, Jonas Kohler, Michael F. Cohen
2025 J jnl
Storybooth: Training-free Multi-Subject Consistency for Improved Visual Storytelling.
CoRR
Jaskirat Singh, Junshen Kevin Chen, Jonas Kohler, Michael F. Cohen
2024 A* conf
Cache Me if You Can: Accelerating Diffusion Models through Block Caching.
CVPR
Felix Wimbauer, Bichen Wu, Edgar Schönfeld, Xiaoliang Dai, Ji Hou, Zijian He, Artsiom Sanakoyeu, Peizhao Zhang, Sam S. Tsai, Jonas Kohler, Christian Rupprecht, Daniel Cremers, Peter Vajda, Jialiang Wang
2024 J jnl
Deep learning applied to the segmentation of rodent brain MRI data outperforms noisy ground truth on full-fledged brain atlases.
NeuroImage
Jonas Kohler, Thomas Bielser, Stanislaw Adaszewski, Basil Künnecke, Andreas Bruns
2024 J jnl
Imagine Flash: Accelerating Emu Diffusion Models with Backward Distillation.
CoRR
Jonas Kohler, Albert Pumarola, Edgar Schönfeld, Artsiom Sanakoyeu, Roshan Sumbaly, Peter Vajda, Ali K. Thabet
2023 J jnl
Adaptive Guidance: Training-free Acceleration of Conditional Diffusion Models.
CoRR
Angela Castillo, Jonas Kohler, Juan C. Pérez, Juan Pablo Pérez, Albert Pumarola, Bernard Ghanem, Pablo Arbeláez, Ali K. Thabet
2023 J jnl
Cache Me if You Can: Accelerating Diffusion Models through Block Caching.
CoRR
Felix Wimbauer, Bichen Wu, Edgar Schönfeld, Xiaoliang Dai, Ji Hou, Zijian He, Artsiom Sanakoyeu, Peizhao Zhang, Sam S. Tsai, Jonas Kohler, Christian Rupprecht, Daniel Cremers, Peter Vajda, Jialiang Wang
2023 J jnl
fMPI: Fast Novel View Synthesis in the Wild with Layered Scene Representations.
CoRR
Jonas Kohler, Nicolas Griffiths Sanchez, Luca Cavalli, Catherine Herold, Albert Pumarola, Alberto Garcia Garcia, Ali K. Thabet
2022 — —
Insights on the interplay of network architectures and optimization algorithms in deep learning.
Jonas Kohler
2022 A conf
Vanishing Curvature in Randomly Initialized Deep ReLU Networks.
AISTATS
Antonio Orvieto, Jonas Kohler, Dario Pavllo, Thomas Hofmann, Aurélien Lucchi
2021 A* conf
Learning Generative Models of Textured 3D Meshes from Real-World Images.
ICCV
Dario Pavllo, Jonas Kohler, Thomas Hofmann, Aurélien Lucchi
2021 J jnl
Learning Generative Models of Textured 3D Meshes from Real-World Images.
CoRR
Dario Pavllo, Jonas Kohler, Thomas Hofmann, Aurélien Lucchi
2021 J jnl
Safe Deep Reinforcement Learning for Multi-Agent Systems with Continuous Action Spaces.
CoRR
Ziyad Sheebaelhamd, Konstantinos Zisis, Athina Nisioti, Dimitris Gkouletsos, Dario Pavllo, Jonas Kohler
2021 J jnl
Synthesizing Speech from Intracranial Depth Electrodes using an Encoder-Decoder Framework.
CoRR
Jonas Kohler, Maarten C. Ottenhoff, Sophocles Goulis, Miguel Angrick, Albert J. Colon, G. Louis Wagner, Simon Tousseyn, Pieter Leonard Kubben, Christian Herff
2021 J jnl
This Looks Like That... Does it? Shortcomings of Latent Space Prototype Interpretability in Deep Networks.
CoRR
Adrian Hoffmann, Claudio Fanconi, Rahul Rade, Jonas Kohler
2021 J jnl
Vanishing Curvature and the Power of Adaptive Methods in Randomly Initialized Deep Networks.
CoRR
Antonio Orvieto, Jonas Kohler, Dario Pavllo, Thomas Hofmann, Aurélien Lucchi
2020 J jnl
Two-Level K-FAC Preconditioning for Deep Learning.
CoRR
Nikolaos Tselepidis, Jonas Kohler, Antonio Orvieto
2019 J jnl
A Stochastic Tensor Method for Non-convex Optimization.
CoRR
Aurélien Lucchi, Jonas Kohler
2019 J jnl
Ellipsoidal Trust Region Methods and the Marginal Value of Hessian Information for Neural Network Training.
CoRR
Leonard Adolphs, Jonas Kohler, Aurélien Lucchi
2019 A conf
The Role of Memory in Stochastic Optimization.
UAI
Antonio Orvieto, Jonas Kohler, Aurélien Lucchi
2019 J jnl
The Role of Memory in Stochastic Optimization.
CoRR
Antonio Orvieto, Jonas Kohler, Aurélien Lucchi