{"total":2005,"rows":[{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673,"area":null},{"id":"2306.00978","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","created":"2023-06-01","cited_by_count":1298,"area":null},{"id":"2106.10199","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","created":"2021-06-18","cited_by_count":1245,"area":null},{"id":"2301.00774","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","created":"2023-01-02","cited_by_count":1121,"area":null},{"id":"2306.11695","title":"A Simple and Effective Pruning Approach for Large Language Models","created":"2023-06-20","cited_by_count":800,"area":null},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764,"area":null},{"id":"2311.03099","title":"Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch","created":"2023-11-06","cited_by_count":694,"area":null},{"id":"2403.14608","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","created":"2024-03-21","cited_by_count":656,"area":null},{"id":"2203.02053","title":"Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning","created":"2022-03-03","cited_by_count":561,"area":null},{"id":"2111.11426","title":"Neural Fields in Visual Computing and Beyond","created":"2021-11-22","cited_by_count":540,"area":null},{"id":"2305.07759","title":"TinyStories: How Small Can Language Models Be and Still Speak Coherent English?","created":"2023-05-12","cited_by_count":449,"area":null},{"id":"2311.17245","title":"LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS","created":"2023-11-28","cited_by_count":436,"area":null},{"id":"2310.06694","title":"Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning","created":"2023-10-10","cited_by_count":415,"area":null},{"id":"2106.14806","title":"Laplace Redux -- Effortless Bayesian Deep Learning","created":"2021-06-28","cited_by_count":365,"area":null},{"id":"2310.11454","title":"VeRA: Vector-based Random Matrix Adaptation","created":"2023-10-17","cited_by_count":300,"area":null},{"id":"2110.06296","title":"The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks","created":"2021-10-12","cited_by_count":291,"area":null},{"id":"2111.11326","title":"DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion","created":"2021-11-22","cited_by_count":291,"area":null},{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269,"area":null},{"id":"2101.09671","title":"Pruning and Quantization for Deep Neural Network Acceleration: A Survey","created":"2021-01-24","cited_by_count":263,"area":null},{"id":"2310.17157","title":"Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time","created":"2023-10-26","cited_by_count":252,"area":null},{"id":"2206.06522","title":"LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning","created":"2022-06-13","cited_by_count":230,"area":null},{"id":"2312.12148","title":"Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment","created":"2023-12-19","cited_by_count":230,"area":null},{"id":"2111.09839","title":"Training Neural Networks with Fixed Sparse Masks","created":"2021-11-18","cited_by_count":214,"area":null},{"id":"2307.05695","title":"ReLoRA: High-Rank Training Through Low-Rank Updates","created":"2023-07-11","cited_by_count":204,"area":null},{"id":"2308.06767","title":"A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations","created":"2023-08-13","cited_by_count":202,"area":null},{"id":"2101.08134","title":"Zero-Cost Proxies for Lightweight NAS","created":"2021-01-20","cited_by_count":199,"area":null},{"id":"2312.04564","title":"EAGLES: Efficient Accelerated 3D Gaussians with Lightweight EncodingS","created":"2023-12-07","cited_by_count":196,"area":null},{"id":"2106.04533","title":"Chasing Sparsity in Vision Transformers: An End-to-End Exploration","created":"2021-06-08","cited_by_count":183,"area":null},{"id":"2102.04010","title":"Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch","created":"2021-02-08","cited_by_count":179,"area":null},{"id":"2207.09353","title":"Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communications","created":"2022-07-19","cited_by_count":175,"area":null},{"id":"2204.00408","title":"Structured Pruning Learns Compact and Accurate Models","created":"2022-04-01","cited_by_count":170,"area":null},{"id":"2310.05175","title":"Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity","created":"2023-10-08","cited_by_count":165,"area":null},{"id":"2204.09656","title":"A Fast Post-Training Pruning Framework for Transformers","created":"2022-03-29","cited_by_count":162,"area":null},{"id":"2306.17844","title":"The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks","created":"2023-06-30","cited_by_count":156,"area":null},{"id":"2402.18815","title":"How do Large Language Models Handle Multilingualism?","created":"2024-02-29","cited_by_count":150,"area":null},{"id":"2204.06487","title":"Adapting Pre-trained Language Models to African Languages via Multilingual Adaptive Fine-Tuning","created":"2022-04-13","cited_by_count":149,"area":null},{"id":"2110.07560","title":"Composable Sparse Fine-Tuning for Cross-Lingual Transfer","created":"2021-10-14","cited_by_count":144,"area":null},{"id":"2309.00667","title":"Taken out of context: On measuring situational awareness in LLMs","created":"2023-09-01","cited_by_count":143,"area":null},{"id":"2207.03620","title":"More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity","created":"2022-07-07","cited_by_count":142,"area":null},{"id":"2303.13506","title":"The Quantization Model of Neural Scaling","created":"2023-03-23","cited_by_count":138,"area":null},{"id":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129,"area":null},{"id":"2105.12221","title":"Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances","created":"2021-05-25","cited_by_count":127,"area":null},{"id":"2305.01649","title":"Generalizing Dataset Distillation via Deep Generative Prior","created":"2023-05-02","cited_by_count":126,"area":null},{"id":"2303.00566","title":"Structured Pruning for Deep Convolutional Neural Networks: A survey","created":"2023-03-01","cited_by_count":122,"area":null},{"id":"2410.19735","title":"Model merging with SVD to tie the Knots","created":"2024-10-25","cited_by_count":122,"area":null},{"id":"2211.08403","title":"REPAIR: REnormalizing Permuted Activations for Interpolation Repair","created":"2022-11-15","cited_by_count":120,"area":null},{"id":"2102.06790","title":"A Unified Lottery Ticket Hypothesis for Graph Neural Networks","created":"2021-02-12","cited_by_count":118,"area":null},{"id":"2402.11592","title":"Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark","created":"2024-02-18","cited_by_count":114,"area":null},{"id":"2105.06990","title":"BERT Busters: Outlier Dimensions that Disrupt Transformers","created":"2021-05-14","cited_by_count":112,"area":null},{"id":"2102.02887","title":"Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training","created":"2021-02-04","cited_by_count":110,"area":null},{"id":"2104.08762","title":"Case-based Reasoning for Natural Language Queries over Knowledge Bases","created":"2021-04-18","cited_by_count":107,"area":null},{"id":"2204.00595","title":"Monarch: Expressive Structured Matrices for Efficient and Accurate Training","created":"2022-04-01","cited_by_count":106,"area":null},{"id":"2302.06600","title":"Task-Specific Skill Localization in Fine-tuned Language Models","created":"2023-02-13","cited_by_count":105,"area":null},{"id":"2102.08124","title":"Accelerated Sparse Neural Training: A Provable and Efficient Method to Find N:M Transposable Masks","created":"2021-02-16","cited_by_count":103,"area":null},{"id":"2205.14083","title":"Sharpness-Aware Training for Free","created":"2022-05-27","cited_by_count":95,"area":null},{"id":"2309.15698","title":"Deep Model Fusion: A Survey","created":"2023-09-27","cited_by_count":91,"area":null},{"id":"2212.09535","title":"BLOOM+1: Adding Language Support to BLOOM for Zero-Shot Prompting","created":"2022-12-19","cited_by_count":90,"area":null},{"id":"2309.12314","title":"TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance","created":"2023-09-21","cited_by_count":90,"area":null},{"id":"2402.09371","title":"Transformers Can Achieve Length Generalization But Not Robustly","created":"2024-02-14","cited_by_count":86,"area":null},{"id":"2402.16842","title":"Asymmetry in Low-Rank Adapters of Foundation Models","created":"2024-02-26","cited_by_count":86,"area":null},{"id":"2202.02643","title":"The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training","created":"2022-02-05","cited_by_count":85,"area":null},{"id":"2103.05633","title":"Proof-of-Learning: Definitions and Practice","created":"2021-03-09","cited_by_count":84,"area":null},{"id":"2106.10404","title":"Sparse Training via Boosting Pruning Plasticity with Neuroregeneration","created":"2021-06-19","cited_by_count":84,"area":null},{"id":"2210.04284","title":"SparseAdapter: An Easy Approach for Improving the Parameter-Efficiency of Adapters","created":"2022-10-09","cited_by_count":83,"area":null},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"area":null},{"id":"2108.13138","title":"Neuron-level Interpretation of Deep NLP Models: A Survey","created":"2021-08-30","cited_by_count":81,"area":null},{"id":"2406.11617","title":"DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling","created":"2024-06-17","cited_by_count":81,"area":null},{"id":"2302.14017","title":"Full Stack Optimization of Transformer Inference: a Survey","created":"2023-02-27","cited_by_count":80,"area":null},{"id":"2106.03517","title":"Top-KAST: Top-K Always Sparse Training","created":"2021-06-07","cited_by_count":79,"area":null},{"id":"2110.14032","title":"MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge","created":"2021-10-26","cited_by_count":79,"area":null},{"id":"2206.12562","title":"PLATON: Pruning Large Transformer Models with Upper Confidence Bound of Weight Importance","created":"2022-06-25","cited_by_count":79,"area":null},{"id":"2410.20672","title":"Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRA","created":"2024-10-28","cited_by_count":78,"area":null},{"id":"2112.00029","title":"Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models","created":"2021-11-30","cited_by_count":76,"area":null},{"id":"2310.02025","title":"DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training","created":"2023-10-03","cited_by_count":76,"area":null},{"id":"2106.02890","title":"Can Subnetwork Structure be the Key to Out-of-Distribution Generalization?","created":"2021-06-05","cited_by_count":75,"area":null},{"id":"2206.00187","title":"DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Training","created":"2022-06-01","cited_by_count":74,"area":null},{"id":"2103.14636","title":"A Practical Survey on Faster and Lighter Transformers","created":"2021-03-26","cited_by_count":73,"area":null},{"id":"2107.07467","title":"Only Train Once: A One-Shot Neural Network Training And Pruning Framework","created":"2021-07-15","cited_by_count":70,"area":null},{"id":"2111.13171","title":"Intrinsic Dimension, Persistent Homology and Generalization in Neural Networks","created":"2021-11-25","cited_by_count":70,"area":null},{"id":"2206.04030","title":"High-dimensional limit theorems for SGD: Effective dynamics and critical scaling","created":"2022-06-08","cited_by_count":70,"area":null},{"id":"2210.05177","title":"Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach","created":"2022-10-11","cited_by_count":70,"area":null},{"id":"2302.14040","title":"Permutation Equivariant Neural Functionals","created":"2023-02-27","cited_by_count":70,"area":null},{"id":"2307.13770","title":"E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuning","created":"2023-07-25","cited_by_count":70,"area":null},{"id":"2201.07395","title":"Overview frequency principle/spectral bias in deep learning","created":"2022-01-19","cited_by_count":69,"area":null},{"id":"2307.09218","title":"A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning","created":"2023-07-16","cited_by_count":69,"area":null},{"id":"2210.05337","title":"SGD with Large Step Sizes Learns Sparse Features","created":"2022-10-11","cited_by_count":68,"area":null},{"id":"2111.05754","title":"Prune Once for All: Sparse Pre-Trained Language Models","created":"2021-11-10","cited_by_count":66,"area":null},{"id":"2106.04690","title":"Handcrafted Backdoors in Deep Neural Networks","created":"2021-06-08","cited_by_count":63,"area":null},{"id":"2302.05438","title":"Deep Learning on Implicit Neural Representations of Shapes","created":"2023-02-10","cited_by_count":63,"area":null},{"id":"2103.03014","title":"Lost in Pruning: The Effects of Pruning Neural Networks beyond Test Accuracy","created":"2021-03-04","cited_by_count":62,"area":null},{"id":"2106.09129","title":"A Winning Hand: Compressing Deep Networks Can Improve Out-Of-Distribution Robustness","created":"2021-06-16","cited_by_count":62,"area":null},{"id":"2302.06646","title":"Simple Hardware-Efficient Long Convolutions for Sequence Modeling","created":"2023-02-13","cited_by_count":62,"area":null},{"id":"2504.12782","title":"Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted Concepts","created":"2025-04-17","cited_by_count":62,"area":null},{"id":"2103.03936","title":"Pufferfish: Communication-efficient Models At No Extra Cost","created":"2021-03-05","cited_by_count":61,"area":null},{"id":"2206.10369","title":"The State of Sparse Training in Deep Reinforcement Learning","created":"2022-06-17","cited_by_count":61,"area":null},{"id":"2310.08915","title":"Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs","created":"2023-10-13","cited_by_count":61,"area":null},{"id":"2105.03361","title":"What Kinds of Functions do Deep Neural Networks Learn? Insights from Variational Spline Theory","created":"2021-05-07","cited_by_count":60,"area":null},{"id":"2106.12379","title":"AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks","created":"2021-06-23","cited_by_count":59,"area":null},{"id":"2105.12002","title":"Super Tickets in Pre-Trained Language Models: From Model Compression to Improving Generalization","created":"2021-05-25","cited_by_count":56,"area":null},{"id":"2210.04092","title":"Advancing Model Pruning via Bi-level Optimization","created":"2022-10-08","cited_by_count":56,"area":null}],"next_cursor":"100"}