Optimization & Theory

The Expressive Power of Tuning Only the Normalization Layers COLT 2023 The Framework Tax: Disparities Between Inference Efficiency in NLP Research and Deployment EMNLP 2023 The Hessian perspective into the Nature of Convolutional Neural Networks ICML 2023 The Implicit Bias of Batch Normalization in Linear Models and Two-layer Linear Convolutional Neural Networks COLT 2023 The Implicit Regularization of Dynamical Stability in Stochastic Gradient Descent ICML 2023 The Implicit Regularization of Momentum Gradient Descent in Overparametrized Models AAAI 2023 The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers ICLR 2023 The NLP Task Effectiveness of Long-Range Transformers EACL 2023 Theoretical and Practical Perspectives on what Influence Functions Do NeurIPS 2023 This Looks Like Those: Illuminating Prototypical Concepts Using Multiple Visualizations NeurIPS 2023 Three Guidelines You Should Know for Universally Slimmable Self-Supervised Learning CVPR 2023 Time-synchronous one-pass Beam Search for Parallel Online and Offline Transducers with Dynamic Block Training Interspeech 2023 TinyNeRF: Towards 100 x Compression of Voxel Radiance Fields AAAI 2023 TIPI: Test Time Adaptation With Transformation Invariance CVPR 2023 TIPS: Topologically Important Path Sampling for Anytime Neural Networks ICML 2023 TokenDrop + BucketSampler: Towards Efficient Padding-free Fine-tuning of Language Models EMNLP 2023 Tokenization and the Noiseless Channel ACL 2023 Token-Level Self-Evolution Training for Sequence-to-Sequence Learning ACL 2023 Top-Ambiguity Samples Matter: Understanding Why Deep Ensemble Works in Selective Classification NeurIPS 2023 Toward Human-Like Evaluation for Natural Language Generation with Error Analysis ACL 2023 Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models EMNLP 2023 Towards Being Parameter-Efficient: A Stratified Sparsely Activated Transformer with Dynamic Capacity EMNLP 2023 Towards Better Visualizing the Decision Basis of Networks via Unfold and Conquer Attribution Guidance AAAI 2023 Towards Constituting Mathematical Structures for Learning to Optimize ICML 2023 Towards Effective Adversarial Textured 3D Meshes on Physical Face Recognition CVPR 2023