TS
Tim Salimans
cs.LGstat.MLcs.CVcs.AIstat.COcs.NEastro-ph.COastro-ph.IMcs.ITcs.SD
On Valency
published · living versionsW_xfn54jr2·v1 · currentpublished
Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks
with Diederik P. Kingma
1 version
Preprints & journals
50 papers in the corpus · 2013–2026Dual-Rate Diffusion: Accelerating diffusion models with an interleaved heavy-light network2605.18190v1 · Grigory Bartosh, David Ruhe, Emiel Hoogeboom et al.2026 · 0 citationsarXiv
Covariance-aware sampling for Diffusion Models2605.13910v1 · Andrea Schioppa, Tim Salimans2026 · 0 citationsarXiv
Beyond Single Tokens: Distilling Discrete Diffusion Models via Discrete MMD2603.20155v1 · Emiel Hoogeboom, David Ruhe, Jonathan Heek et al.2026 · 0 citationsarXiv
Unified Latents (UL): How to train your latents2602.17270v1 · Jonathan Heek, Emiel Hoogeboom, Thomas Mensink et al.2026 · 0 citationsarXiv
Simpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusion2410.19324v2 · Emiel Hoogeboom, Thomas Mensink, Jonathan Heek et al.2024 · 0 citationsarXiv
EM Distillation for One-step Diffusion Models2405.16852v2 · Sirui Xie, Zhisheng Xiao, Diederik P Kingma et al.2024 · 1 citationarXiv
Multistep Consistency Models2403.06807v3 · Jonathan Heek, Emiel Hoogeboom, Tim Salimans2024 · 3 citationsarXiv
Rolling Diffusion Models2402.09470v3 · David Ruhe, Jonathan Heek, Tim Salimans et al.2024 · 1 citationarXiv
Multistep Distillation of Diffusion Models via Moment Matching2406.04103v1 · Tim Salimans, Thomas Mensink, Jonathan Heek et al.2024 · 2 citationsarXiv
Blurring Diffusion Models2209.05557v3 · Emiel Hoogeboom, Tim Salimans2022 · 11 citationsarXiv
Simple diffusion: End-to-end diffusion for high resolution images2301.11093v2 · Emiel Hoogeboom, Jonathan Heek, Tim Salimans2023 · 27 citationsarXiv
Variational Diffusion Models2107.00630v6 · Diederik P. Kingma, Tim Salimans, Ben Poole et al.2021 · 282 citationsarXiv
On Distillation of Guided Diffusion Models2210.03142v3 · Chenlin Meng, Robin Rombach, Ruiqi Gao et al.2022 · 309 citationsarXiv
Image Super-Resolution via Iterative Refinement.36094974 · Saharia, Chitwan, Ho, Jonathan, Chan, William et al.2023 · 1,789 citationsIEEE transactions on pattern analysis and machine intelligence. 2023;45(4):4713-4726
Lossy Compression with Gaussian Diffusion2206.08889v2 · Lucas Theis, Tim Salimans, Matthew D. Hoffman et al.2022 · 19 citationsarXiv
Imagen Video: High Definition Video Generation with Diffusion Models2210.02303v1 · Jonathan Ho, William Chan, Chitwan Saharia et al.2022 · 346 citationsarXiv
Classifier-Free Diffusion Guidance2207.12598v1 · Jonathan Ho, Tim Salimans2022 · 755 citationsarXiv
Video Diffusion Models2204.03458v2 · Jonathan Ho, Tim Salimans, Alexey Gritsenko et al.2022 · 0 citationsarXiv
Progressive Distillation for Fast Sampling of Diffusion Models2202.00512v2 · Tim Salimans, Jonathan Ho2022 · 186 citationsarXiv
Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding2205.11487v1 · Chitwan Saharia, William Chan, Saurabh Saxena et al.2022 · 2,561 citationsarXiv
Palette: Image-to-Image Diffusion Models2111.05826v2 · Chitwan Saharia, William Chan, Huiwen Chang et al.2021 · 1,636 citationsarXiv
Autoregressive Diffusion Models2110.02037v2 · Emiel Hoogeboom, Alexey A. Gritsenko, Jasmijn Bastings et al.2021 · 1 citationarXiv
Cascaded Diffusion Models for High Fidelity Image Generation2106.15282v3 · Jonathan Ho, Chitwan Saharia, William Chan et al.2021 · 448 citationsarXiv
Image Super-Resolution via Iterative Refinement2104.07636v2 · Chitwan Saharia, Jonathan Ho, William Chan et al.2021 · 1,789 citationsarXiv
The Likelihood of Mixed Hitting Times1905.03463v2 · Jaap H. Abbring, Tim Salimans2019 · 4 citationsarXiv
Agent-Centric Representations for Multi-Agent Reinforcement Learning2104.09402v1 · Wenling Shang, Lasse Espeholt, Anton Raichuk et al.2021 · 7 citationsarXiv
IDF++: Analyzing and Improving Integer Discrete Flows for Lossless Compression2006.12459v2 · Rianne van den Berg, Alexey A. Gritsenko, Mostafa Dehghani et al.2020 · 44 citationsarXiv
Hydra: Preserving Ensemble Diversity for Model Distillation2001.04694v2 · Linh Tran, Bastiaan S. Veeling, Kevin Roth et al.2020 · 33 citationsarXiv
Dota 2 with Large Scale Deep Reinforcement Learning1912.06680v1 · OpenAI: Christopher Berner, Greg Brockman, Brooke Chan et al.2019 · 1,036 citationsarXiv
A Spectral Energy Distance for Parallel Speech Synthesis2008.01160v2 · Alexey A. Gritsenko, Tim Salimans, Rianne van den Berg et al.2020 · 19 citationsarXiv
The k-tied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks2002.02655v2 · Jakub Swiatkowski, Kevin Roth, Bastiaan S. Veeling et al.2020 · 27 citationsarXiv
How Good is the Bayes Posterior in Deep Neural Networks Really?2002.02405v2 · Florian Wenzel, Kevin Roth, Bastiaan S. Veeling et al.2020 · 33 citationsarXiv
Milking CowMask for Semi-Supervised Image Classification2003.12022v3 · Geoff French, Avital Oliver, Tim Salimans2020 · 22 citationsarXiv
MetNet: A Neural Weather Model for Precipitation Forecasting2003.12140v2 · Casper Kaae S\onderby, Lasse Espeholt, Jonathan Heek et al.2020 · 308 citationsarXiv
Axial Attention in Multidimensional Transformers1912.12180v1 · Jonathan Ho, Nal Kalchbrenner, Dirk Weissenborn et al.2019 · 364 citationsarXiv
Policy Gradient Search: Online Planning and Expert Iteration without Search Trees1904.03646v1 · Thomas Anthony, Robert Nishihara, Philipp Moritz et al.2019 · 19 citationsarXiv
Learning Montezuma's Revenge from a Single Demonstration1812.03381v1 · Tim Salimans, Richard Chen2018 · 80 citationsarXiv
Improving GANs Using Optimal Transport1803.05573v1 · Tim Salimans, Han Zhang, Alec Radford et al.2018 · 45 citationsarXiv
Evolution Strategies as a Scalable Alternative to Reinforcement Learning1703.03864v2 · Tim Salimans, Jonathan Ho, Xi Chen et al.2017 · 990 citationsarXiv
Variational Lossy Autoencoder1611.02731v2 · Xi Chen, Diederik P. Kingma, Tim Salimans et al.2016 · 241 citationsarXiv
Improving Variational Inference with Inverse Autoregressive Flow1606.04934v2 · Diederik P. Kingma, Tim Salimans, Rafal Jozefowicz et al.2016 · 180 citationsarXiv
PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications1701.05517v1 · Tim Salimans, Andrej Karpathy, Xi Chen et al.2017 · 614 citationsarXiv
Improved Techniques for Training GANs1606.03498v1 · Tim Salimans, Ian Goodfellow, Wojciech Zaremba et al.2016 · 1,344 citationsarXiv
Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks1602.07868v3 · Tim Salimans, Diederik P. Kingma2016 · 1,429 citationsarXivon Valency
A Structured Variational Auto-encoder for Learning Deep Hierarchies of Sparse Features1602.08734v1 · Tim Salimans2016 · 10 citationsarXiv
Variational Dropout and the Local Reparameterization Trick1506.02557v2 · Diederik P. Kingma, Tim Salimans, Max Welling2015 · 440 citationsarXiv
Markov Chain Monte Carlo and Variational Inference: Bridging the Gap1410.6460v4 · Tim Salimans, Diederik P. Kingma, Max Welling2014 · 384 citationsarXivon Valency
On Using Control Variates with Stochastic Approximation for Variational Bayes and its Connection to Stochastic Linear Regression1401.1022v3 · Tim Salimans, David A. Knowles2014 · 18 citationsarXiv
Implementing and Automating Fixed-Form Variational Posterior Approximation through Stochastic Linear Regression1401.2135v1 · Tim Salimans2014 · 0 citationsarXiv
Observing Dark Worlds: A crowdsourcing experiment for dark matter mapping1311.0704v1 · David Harvey, Thomas D. Kitching, Joyce Noah-Vanhoucke et al.2013 · 18 citationsarXiv
Career total: 70 works. 50 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.