memory efficiency

PatchDropout: Economizing Vision Transformers Using Patch Dropout WACV 2023 Pit One Against Many: Leveraging Attention-head Embeddings for Parameter-efficient Multi-head Attention EMNLP 2023 PlenVDB: Memory Efficient VDB-Based Radiance Fields for Fast Training and Rendering CVPR 2023 Pre-computed memory or on-the-fly encoding? A hybrid approach to retrieval augmentation makes the most of your compute ICML 2023 Random-Access Infinite Context Length for Transformers NeurIPS 2023 Reversible Neural Networks for Memory-Efficient Speaker Verification Interspeech 2023 Revisiting Block-based Quantisation: What is Important for Sub-8-bit LLM Inference? EMNLP 2023 ROME: Robustifying Memory-Efficient NAS via Topology Disentanglement and Gradient Accumulation ICCV 2023 Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time NeurIPS 2023 Self-Attentive Pooling for Efficient Deep Learning WACV 2023 Sequence Parallelism: Long Sequence Training from System Perspective ACL 2023 Single-Pass Pivot Algorithm for Correlation Clustering. Keep it simple! NeurIPS 2023 Singularformer: Learning to Decompose Self-Attention to Linearize the Complexity of Transformer IJCAI 2023 Softmax Output Approximation for Activation Memory-Efficient Training of Attention-based Networks NeurIPS 2023 StreamNet: Memory-Efficient Streaming Tiny Deep Learning Inference on the Microcontroller NeurIPS 2023 Visual Query Tuning: Towards Effective Usage of Intermediate Representations for Parameter and Memory Efficient Transfer Learning CVPR 2023 When to Use Efficient Self Attention? Profiling Text, Speech and Image Transformer Variants ACL 2023 Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model NeurIPS 2023 ALIFE: Adaptive Logit Regularizer and Feature Replay for Incremental Semantic Segmentation NeurIPS 2022 AutoMTL: A Programming Framework for Automating Efficient Multi-Task Learning NeurIPS 2022 Back Razor: Memory-Efficient Transfer Learning by Self-Sparsified Backpropagation NeurIPS 2022 Be Like Water: Adaptive Floating Point for Machine Learning ICML 2022 DIP: Deep Inverse Patchmatch for High-Resolution Optical Flow CVPR 2022 EXACT: Scalable Graph Neural Networks Training via Extreme Activation Compression ICLR 2022 Generalized Binary Search Network for Highly-Efficient Multi-View Stereo CVPR 2022