training efficiency

CoMERA: Computing- and Memory-Efficient Training via Rank-Adaptive Tensor Optimization NeurIPS 2024 Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum NeurIPS 2024 DeepSpeed Data Efficiency: Improving Deep Learning Model Quality and Training Efficiency via Efficient Data Sampling and Routing AAAI 2024 DropBP: Accelerating Fine-Tuning of Large Language Models by Dropping Backward Propagation NeurIPS 2024 Efficient Dynamic Hard Negative Sampling for Dialogue Selection ACL 2024 Elucidating the Design Space of Dataset Condensation NeurIPS 2024 Improving Neural Logic Machines via Failure Reflection ICML 2024 Improving Training Efficiency of Diffusion Models via Multi-Stage Framework and Tailored Multi-Decoder Architecture CVPR 2024 Learning from Imperfect Data: Towards Efficient Knowledge Distillation of Autoregressive Language Models for Text-to-SQL EMNLP 2024 Multisize Dataset Condensation ICLR 2024 Nonparametric Teaching of Implicit Neural Representations ICML 2024 Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference NeurIPS 2024 SoftDedup: an Efficient Data Reweighting Method for Speeding Up Language Model Pre-training ACL 2024 Think Before You Act: Decision Transformers with Working Memory ICML 2024 Time- Memory- and Parameter-Efficient Visual Adaptation CVPR 2024 Data Pruning via Moving-one-Sample-out NeurIPS 2023 Efficient NLP Model Finetuning via Multistage Data Filtering IJCAI 2023 EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbones ICCV 2023 Eva: Practical Second-order Optimization with Kronecker-vectorized Approximation ICLR 2023 KAKURENBO: Adaptively Hiding Samples in Deep Neural Network Training NeurIPS 2023 Learning to Boost Training by Periodic Nowcasting Near Future Weights ICML 2023 Mitigating the Burden of Redundant Datasets via Batch-Wise Unique Samples and Frequency-Aware Losses ACL 2023 Quick Back-Translation for Unsupervised Machine Translation EMNLP 2023 Re-parameterizing Your Optimizers rather than Architectures ICLR 2023 Towards Memory- and Time-Efficient Backpropagation for Training Spiking Neural Networks ICCV 2023