Efficient Computing

MAGNOLIA: Matching Algorithms via GNNs for Online Value-to-go Approximation ICML 2024 MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization NeurIPS 2024 MAIR: A Massive Benchmark for Evaluating Instructed Retrieval EMNLP 2024 Make Bricks with a Little Straw: Large-Scale Spatio-Temporal Graph Learning with Restricted GPU-Memory Capacity IJCAI 2024 Make Large Language Model a Better Ranker EMNLP 2024 Make Some Noise: Unlocking Language Model Parallel Inference Capability through Noisy Training EMNLP 2024 MambaSCI: Efficient Mamba-UNet for Quad-Bayer Patterned Video Snapshot Compressive Imaging NeurIPS 2024 MA-Net: Rethinking Neural Unit in the Light of Astrocytes AAAI 2024 MAPE-PPI: Towards Effective and Efficient Protein-Protein Interaction Prediction via Microenvironment-Aware Protein Embedding ICLR 2024 MapLE: Matching Molecular Analogues Promptly with Low Computational Resources by Multi-Metrics Evaluation (Student Abstract) AAAI 2024 MAPLE: Multilingual Evaluation of Parameter Efficient Finetuning of Large Language Models ACL 2024 MassSpecGym: A benchmark for the discovery and identification of molecules NeurIPS 2024 MAST: Global Scheduling of ML Training across Geo-Distributed Datacenters at Hyperscale OSDI 2024 MATES: Model-Aware Data Selection for Efficient Pretraining with Data Influence Models NeurIPS 2024 MatFormer: Nested Transformer for Elastic Inference NeurIPS 2024 MathAttack: Attacking Large Language Models towards Math Solving Ability AAAI 2024 MATHSENSEI: A Tool-Augmented Large Language Model for Mathematical Reasoning NAACL 2024 Matryoshka-Adaptor: Unsupervised and Supervised Tuning for Smaller Embedding Dimensions EMNLP 2024 Matryoshka Query Transformer for Large Vision-Language Models NeurIPS 2024 MaxQ: Multi-Axis Query for N:M Sparsity Network CVPR 2024 MCAD: Multi-teacher Cross-modal Alignment Distillation for efficient image-text retrieval NAACL 2024 Measuring Per-Unit Interpretability at Scale Without Humans NeurIPS 2024 Mechanistic Design and Scaling of Hybrid Architectures ICML 2024 Mechanistic Neural Networks for Scientific Machine Learning ICML 2024 Med-DANet V2: A Flexible Dynamic Architecture for Efficient Medical Volumetric Segmentation WACV 2024