pith. sign in

Dmitry Vetrov

Identifiers

  • name variant Dmitry Vetrov 0.60 · backfill

Papers (37)

  1. How to Train Your Latent Diffusion Language Model Jointly With the Latent Space cs.CL · 2026 · author #7
  2. Why Gaussian Diffusion Models Fail on Discrete Data and How to Prevent It? cs.CL · 2026 · author #5
  3. Can Stationary Distributions of Scale-Invariant Neural Networks Be Described by the Thermodynamics of an Ideal Gas? cs.LG · 2025 · author #6
  4. Smoothie: Smoothing Diffusion on Token Embeddings for Text Generation cs.CL · 2025 · author #3
  5. Subspace Inference for Bayesian Deep Learning cs.LG · 2019 · author #5
  6. The Implicit Metropolis-Hastings Algorithm stat.ML · 2019 · author #3
  7. Importance Weighted Hierarchical Variational Inference stat.ML · 2019 · author #2
  8. User-Controllable Multi-Texture Synthesis with Generative Adversarial Networks cs.CV · 2019 · author #6
  9. Bayesian Sparsification of Gated Recurrent Neural Networks cs.LG · 2018 · author #3
  10. ReSet: Learning Recurrent Dynamic Routing in ResNet-like Neural Networks stat.ML · 2018 · author #3
  11. Variational Dropout via Empirical Bayes stat.ML · 2018 · author #3
  12. Bayesian Compression for Natural Language Processing cs.CL · 2018 · author #3
  13. Metropolis-Hastings view on variational inference and adversarial training stat.ML · 2018 · author #4
  14. The Deep Weight Prior stat.ML · 2018 · author #4
  15. Pairwise Augmented GANs with Adversarial Reconstruction Loss stat.ML · 2018 · author #4
  16. Doubly Semi-Implicit Variational Inference stat.ML · 2018 · author #4
  17. Conditional Generators of Words Definitions cs.CL · 2018 · author #3
  18. Variational Autoencoder with Arbitrary Conditioning stat.ML · 2018 · author #3
  19. Averaging Weights Leads to Wider Optima and Better Generalization cs.LG · 2018 · author #4
  20. Variance Networks: When Expectation Does Not Meet Your Expectations stat.ML · 2018 · author #4
  21. Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs stat.ML · 2018 · author #4
  22. Bayesian Incremental Learning for Deep Neural Networks stat.ML · 2018 · author #6
  23. Uncertainty Estimation via Stochastic Batch Normalization stat.ML · 2018 · author #5
  24. Probabilistic Adaptive Computation Time cs.LG · 2017 · author #3
  25. Bayesian Sparsification of Recurrent Neural Networks stat.ML · 2017 · author #3
  26. Structured Bayesian Pruning via Log-Normal Multiplicative Noise stat.ML · 2017 · author #4
  27. Variational Dropout Sparsifies Deep Neural Networks stat.ML · 2017 · author #3
  28. Spatially Adaptive Computation Time for Residual Networks cs.CV · 2016 · author #6
  29. Robust Variational Inference cs.LG · 2016 · author #3
  30. Ultimate tensorization: compressing convolutional and FC layers alike cs.LG · 2016 · author #4
  31. GTApprox: surrogate modeling for industrial design cs.MS · 2016 · author #6
  32. Tensorizing Neural Networks cs.LG · 2015 · author #4
  33. PerforatedCNNs: Acceleration through Elimination of Redundant Convolutions cs.CV · 2015 · author #3
  34. Breaking Sticks and Ambiguities with Adaptive Skip-gram cs.CL · 2015 · author #4
  35. Submodular relaxation for inference in Markov random fields cs.CV · 2015 · author #2
  36. Multi-utility Learning: Structured-output Learning with Multiple Annotation-specific Loss Functions cs.CV · 2014 · author #2
  37. Submodular Decomposition Framework for Inference in Associative Markov Networks with Global Constraints cs.CV · 2011 · author #2

Mentions

  • 2604.02028 #5 · arxiv_oai · confidence 0.70 Dmitry Vetrov
  • 1103.1077 #2 · backfill · confidence 0.70 Dmitry Vetrov
  • 2505.18853 #3 · arxiv_oai · confidence 0.70 Dmitry Vetrov

Frequent Coauthors