Efficient Computing

You Only Cache Once: Decoder-Decoder Architectures for Language Models NeurIPS 2024 Zero Bubble (Almost) Pipeline Parallelism ICLR 2024 ZeRO++: Extremely Efficient Collective Communication for Large Model Training ICLR 2024 Zero-shot Out-of-domain is No Joke: Lessons Learned in the VoiceMOS 2023 MOS Prediction Challenge Interspeech 2024 Zero-TPrune: Zero-Shot Token Pruning through Leveraging of the Attention Graph in Pre-Trained Transformers CVPR 2024 ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification NeurIPS 2024 μSlope: High Compression and Fast Search on Semi-Structured Logs OSDI 2024 π-Light: Programmatic Interpretable Reinforcement Learning for Resource-Limited Traffic Signal Control AAAI 2024 $\rm A^2Q$: Aggregation-Aware Quantization for Graph Neural Networks ICLR 2023 1% VS 100%: Parameter-Efficient Low Rank Adapter for Dense Predictions CVPR 2023 2-bit Conformer quantization for automatic speech recognition Interspeech 2023 3D UX-Net: A Large Kernel Volumetric ConvNet Modernizing Hierarchical Transformer for Medical Image Segmentation ICLR 2023 5G-IoT Cloud based Demonstration of Real-Time Audio-Visual Speech Enhancement for Multimodal Hearing-aids Interspeech 2023 A2Q: Accumulator-Aware Quantization with Guaranteed Overflow Avoidance ICCV 2023 A benchmark of categorical encoders for binary classification NeurIPS 2023 A Binary Keyword Spotting System with Error-Diffusion Based Feature Binarization Interspeech 2023 ABLATOR: Robust Horizontal-Scaling of Machine Learning Ablation Experiments AutoML 2023 ACA-Net: Towards Lightweight Speaker Verification using Asymmetric Cross Attention Interspeech 2023 AC-Band: A Combinatorial Bandit-Based Approach to Algorithm Configuration AAAI 2023 Accelerated and Sparse Algorithms for Approximate Personalized PageRank and Beyond COLT 2023 Accelerated Coordinate Encoding: Learning to Relocalize in Minutes Using RGB and Poses CVPR 2023 Accelerated On-Device Forward Neural Network Training with Module-Wise Descending Asynchronism NeurIPS 2023 Accelerated Training via Incrementally Growing Neural Networks using Variance Transfer and Learning Rate Adaptation NeurIPS 2023 Accelerating Dataset Distillation via Model Augmentation CVPR 2023 Accelerating the Training of Video Super-resolution Models AAAI 2023