Optimization & Theory

Revisiting Denoising Diffusion Probabilistic Models for Speech Enhancement: Condition Collapse, Efficiency and Refinement AAAI 2023 Revisiting Gradient Clipping: Stochastic bias and tight convergence guarantees ICML 2023 Revisiting Reverse Distillation for Anomaly Detection CVPR 2023 Revisiting Structured Dropout ACML 2023 Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluation ACL 2023 Revisiting Token Dropping Strategy in Efficient BERT Pretraining ACL 2023 RGB No More: Minimally-Decoded JPEG Vision Transformers CVPR 2023 RIFormer: Keep Your Vision Backbone Effective but Removing Token Mixer CVPR 2023 Robust Counterfactual Explanations for Neural Networks With Probabilistic Guarantees ICML 2023 Robust Feature Rectification of Pretrained Vision Models for Object Recognition AAAI 2023 Robust Generalization Against Photon-Limited Corruptions via Worst-Case Sharpness Minimization CVPR 2023 Robustly Learning a Single Neuron via Sharpness ICML 2023 Robust Multiview Point Cloud Registration With Reliable Pose Graph Initialization and History Reweighting CVPR 2023 RobustNeRF: Ignoring Distractors With Robust Losses CVPR 2023 Robustness Guarantees for Adversarially Trained Neural Networks NeurIPS 2023 Rockmate: an Efficient, Fast, Automatic and Generic Tool for Re-materialization in PyTorch ICML 2023 ROME: Robustifying Memory-Efficient NAS via Topology Disentanglement and Gradient Accumulation ICCV 2023 RoMQA: A Benchmark for Robust, Multi-evidence, Multi-answer Question Answering EMNLP 2023 RWKV: Reinventing RNNs for the Transformer Era EMNLP 2023 SAM as an Optimal Relaxation of Bayes ICLR 2023 Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models ICML 2023 SAM operates far from home: eigenvalue regularization as a dynamical phenomenon ICML 2023 Sampling from Gaussian Process Posteriors using Stochastic Gradient Descent NeurIPS 2023 Samsung Research China - Beijing at SemEval-2023 Task 2: An AL-R Model for Multilingual Complex Named Entity Recognition SemEval 2023 Scalable Transformer for PDE Surrogate Modeling NeurIPS 2023