Theory

Tighter Bounds on the Expressivity of Transformer Encoders ICML 2023 Tighter Information-Theoretic Generalization Bounds from Supersamples ICML 2023 Tight Guarantees for Interactive Decision Making with the Decision-Estimation Coefficient COLT 2023 Tight Performance Guarantees of Imitator Policies with Continuous Actions AAAI 2023 To Build Our Future, We Must Know Our Past: Contextualizing Paradigm Shifts in Natural Language Processing EMNLP 2023 Topologically Faithful Image Segmentation via Induced Matching of Persistence Barcodes ICML 2023 Topology-aware Robust Optimization for Out-of-Distribution Generalization ICLR 2023 Toward Better PAC-Bayes Bounds for Uniformly Stable Algorithms NeurIPS 2023 Towards a Unified Theoretical Understanding of Non-contrastive Learning via Rank Differential Mechanism ICLR 2023 Towards Building More Robust NER datasets: An Empirical Study on NER Dataset Bias from a Dataset Difficulty View EMNLP 2023 Towards credible visual model interpretation with path attribution ICML 2023 Towards Equivariant Optical Flow Estimation With Deep Learning WACV 2023 Towards Fair and Comprehensive Comparisons for Image-Based 3D Object Detection ICCV 2023 Towards Interpreting and Utilizing Symmetry Property in Adversarial Examples AAAI 2023 Towards Reliable Neural Specifications ICML 2023 Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective NeurIPS 2023 Towards Safe and Resilient Autonomy in Multi-Robot Systems AAAI 2023 Towards the Difficulty for a Deep Neural Network to Learn Concepts of Different Complexities NeurIPS 2023 Towards Understanding Generalization of Macro-AUC in Multi-label Learning ICML 2023 Towards Understanding the Generalization of Deepfake Detectors from a Game-Theoretical View ICCV 2023 Tracking Most Significant Shifts in Nonparametric Contextual Bandits NeurIPS 2023 Trade-off Between Efficiency and Consistency for Removal-based Explanations NeurIPS 2023 Training Data Extraction From Pre-trained Language Models: A Survey ACL 2023 Training Fully Connected Neural Networks is $\exists\mathbb{R}$-Complete NeurIPS 2023 Training Neural Networks is NP-Hard in Fixed Dimension NeurIPS 2023