Efficient Computing

Unveiling The Matthew Effect Across Channels: Assessing Layer Width Sufficiency via Weight Norm Variance NeurIPS 2024 VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models EMNLP 2024 Weight for Robustness: A Comprehensive Approach towards Optimal Fault-Tolerant Asynchronous ML NeurIPS 2024 What is my quantum computer good for? Quantum capability learning with physics-aware neural networks NeurIPS 2024 Würstchen: An Efficient Architecture for Large-Scale Text-to-Image Diffusion Models ICLR 2024 YaRN: Efficient Context Window Extension of Large Language Models ICLR 2024 Zero-TPrune: Zero-Shot Token Pruning through Leveraging of the Attention Graph in Pre-Trained Transformers CVPR 2024 A Length-Extrapolatable Transformer ACL 2023 Are Random Decompositions all we need in High Dimensional Bayesian Optimisation? ICML 2023 A Unified Optimization Framework of ANN-SNN Conversion: Towards Optimal Mapping from Activation Values to Firing Rates ICML 2023 AutoGraph: Optimizing DNN Computation Graph for Parallel GPU Kernel Execution AAAI 2023 Balanced Column-Wise Block Pruning for Maximizing GPU Parallelism AAAI 2023 Beyond Attentive Tokens: Incorporating Token Importance and Diversity for Efficient Vision Transformers CVPR 2023 Budgeted Training for Vision Transformer ICLR 2023 Carburacy: Summarization Models Tuning and Comparison in Eco-Sustainable Regimes with a Novel Carbon-Aware Accuracy AAAI 2023 CF-ViT: A General Coarse-to-Fine Method for Vision Transformer AAAI 2023 COLA: Orchestrating Error Coding and Learning for Robust Neural Network Inference Against Hardware Defects ICML 2023 CoLT5: Faster Long-Range Transformers with Conditional Computation EMNLP 2023 Consonant is all you need: a compact representation of English text for efficient NLP EMNLP 2023 CQNV: A Combination of Coarsely Quantized Bitstream and Neural Vocoder for Low Rate Speech Coding Interspeech 2023 DynamicDet: A Unified Dynamic Architecture for Object Detection CVPR 2023 Dynamic Transformers Provide a False Sense of Efficiency ACL 2023 Efficient Edge Inference by Selective Query ICLR 2023 Efficient Encoders for Streaming Sequence Tagging EACL 2023 Energy-Efficient Adaptive 3D Sensing CVPR 2023