Techniques

Beyond English-Centric Bitexts for Better Multilingual Language Representation Learning ACL 2023 Beyond Layout Embedding: Layout Attention with Gaussian Biases for Structured Document Understanding EMNLP 2023 Beyond Lipschitz Smoothness: A Tighter Analysis for Nonconvex Optimization ICML 2023 Beyond NaN: Resiliency of Optimization Layers in the Face of Infeasibility AAAI 2023 Beyond probability partitions: Calibrating neural networks with semantic aware grouping NeurIPS 2023 BGL: GPU-Efficient GNN Training by Optimizing Graph Data I/O and Preprocessing NSDI 2023 BiasBed - Rigorous Texture Bias Evaluation CVPR 2023 Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures CVPR 2023 Bidirectionally Deformable Motion Modulation For Video-based Human Pose Transfer ICCV 2023 Bi-directional Masks for Efficient N:M Sparse Training ICML 2023 BigVGAN: A Universal Neural Vocoder with Large-Scale Training ICLR 2023 Binarized Spectral Compressive Imaging NeurIPS 2023 Binaural Sound Localization in Noisy Environments Using Frequency-Based Audio Vision Transformer (FAViT) Interspeech 2023 Biomedical Language Models are Robust to Sub-optimal Tokenization ACL 2023 BIOptimus: Pre-training an Optimal Biomedical Language Model with Curriculum Learning for Named Entity Recognition ACL 2023 BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations EMNLP 2023 Bit Allocation using Optimization ICML 2023 Bit-Pruning: A Sparse Multiplication-Less Dot-Product ICLR 2023 Bit-Shrinking: Limiting Instantaneous Sharpness for Improving Post-Training Quantization CVPR 2023 Bitstream-Corrupted JPEG Images Are Restorable: Two-Stage Compensation and Alignment Framework for Image Restoration CVPR 2023 Black-Box Tuning of Vision-Language Models with Effective Gradient Approximation EMNLP 2023 Blessing of Class Diversity in Pre-training AISTATS 2023 BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing NeurIPS 2023 Block and Subword-Scaling Floating-Point (BSFP) : An Efficient Non-Uniform Quantization For Low Precision Inference ICLR 2023 BLOOM+1: Adding Language Support to BLOOM for Zero-Shot Prompting ACL 2023