conftrace_

Pavel Izmailov

21 papers · 2018–2024 · 7 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓
+10 more ↓ 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (11) 🌍 Conference Polyglot (7)
πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer πŸ† Keyword Champion (2) πŸ—ƒοΈ Keyword Collector (83) ⚑ Prolific Year (6) πŸš€ Conference Pioneer πŸ“ˆ Trend Setter πŸ’Ž Century Club (21) πŸ”₯ Unstoppable (7) ❓ The Questioner (2)

Conferences

NIPS (9) ICML (6) ICLR (2) AISTATS (1) CVPR (1) JMLR (1) UAI (1)

Papers

Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision ICML 2024 FlexiViT: One Model for All Patch Sizes CVPR 2023 Simple and Fast Group Robustness by Automatic Feature Reweighting ICML 2023 Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations ICLR 2023 Bayesian Model Selection, the Marginal Likelihood, and Generalization ICML 2022 On Uncertainty, Tempering, and Data Augmentation in Bayesian Classification NIPS 2022 On Feature Learning in the Presence of Spurious Correlations NIPS 2022 What Are Bayesian Neural Network Posteriors Really Like? ICML 2021 Dangers of Bayesian Model Averaging under Covariate Shift NIPS 2021 Does Knowledge Distillation Really Work? NIPS 2021 Semi-Supervised Learning with Normalizing Flows ICML 2020 Learning Invariances in Neural Networks from Training Data NIPS 2020 Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data ICML 2020 Bayesian Deep Learning and a Probabilistic Perspective of Generalization NIPS 2020 Tensor Train Decomposition on TensorFlow (T3F) JMLR 2020 Why Normalizing Flows Fail to Detect Out-of-Distribution Data NIPS 2020 Subspace Inference for Bayesian Deep Learning UAI 2019 A Simple Baseline for Bayesian Uncertainty in Deep Learning NIPS 2019 There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average ICLR 2019 Scalable Gaussian Processes with Billions of Inducing Inputs via Tensor Train Decomposition AISTATS 2018 Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs NIPS 2018