{"total":264,"rows":[{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380,"area":null},{"id":"2102.04906","title":"Dynamic Neural Networks: A Survey","created":"2021-02-09","cited_by_count":408,"area":null},{"id":"2110.13903","title":"NeRV: Neural Representations for Videos","created":"2021-10-26","cited_by_count":256,"area":null},{"id":"2102.10274","title":"Concealed Object Detection","created":"2021-02-20","cited_by_count":212,"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":"2207.00112","title":"Language model compression with weighted low-rank factorization","created":"2022-06-30","cited_by_count":195,"area":null},{"id":"2111.15667","title":"Adaptive Token Sampling For Efficient Vision Transformers","created":"2021-11-30","cited_by_count":183,"area":null},{"id":"2412.00081","title":"Task Singular Vectors: Reducing Task Interference in Model Merging","created":"2024-11-26","cited_by_count":147,"area":null},{"id":"2103.06255","title":"Involution: Inverting the Inherence of Convolution for Visual Recognition","created":"2021-03-10","cited_by_count":99,"area":null},{"id":"2110.12894","title":"The Efficiency Misnomer","created":"2021-10-25","cited_by_count":98,"area":null},{"id":"2107.06641","title":"Trustworthy AI: A Computational Perspective","created":"2021-07-12","cited_by_count":93,"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":"2211.16386","title":"Compressing Volumetric Radiance Fields to 1 MB","created":"2022-11-29","cited_by_count":68,"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":"2101.06871","title":"CheXtransfer: Performance and Parameter Efficiency of ImageNet Models for Chest X-Ray Interpretation","created":"2021-01-18","cited_by_count":57,"area":null},{"id":"2107.03436","title":"Tensor Methods in Computer Vision and Deep Learning","created":"2021-07-07","cited_by_count":52,"area":null},{"id":"2107.12422","title":"Towards Efficient Tensor Decomposition-Based DNN Model Compression with Optimization Framework","created":"2021-07-26","cited_by_count":52,"area":null},{"id":"2205.05676","title":"Revisiting Random Channel Pruning for Neural Network Compression","created":"2022-05-11","cited_by_count":50,"area":null},{"id":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"area":null},{"id":"2211.12905","title":"GhostNetV2: Enhance Cheap Operation with Long-Range Attention","created":"2022-11-23","cited_by_count":44,"area":null},{"id":"2310.09528","title":"Hypernetwork-based Meta-Learning for Low-Rank Physics-Informed Neural Networks","created":"2023-10-14","cited_by_count":44,"area":null},{"id":"2205.13571","title":"Low-rank lottery tickets: finding efficient low-rank neural networks via matrix differential equations","created":"2022-05-26","cited_by_count":43,"area":null},{"id":"2203.04466","title":"The Combinatorial Brain Surgeon: Pruning Weights That Cancel One Another in Neural Networks","created":"2022-03-09","cited_by_count":41,"area":null},{"id":"2205.05675","title":"NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results","created":"2022-05-11","cited_by_count":40,"area":null},{"id":"2102.10462","title":"BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network Quantization","created":"2021-02-20","cited_by_count":39,"area":null},{"id":"2107.11442","title":"Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition","created":"2021-07-23","cited_by_count":33,"area":null},{"id":"2104.11487","title":"Skip-Convolutions for Efficient Video Processing","created":"2021-04-23","cited_by_count":32,"area":null},{"id":"2204.11786","title":"Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications","created":"2022-04-25","cited_by_count":32,"area":null},{"id":"2401.14109","title":"CompactifAI: Extreme Compression of Large Language Models using Quantum-Inspired Tensor Networks","created":"2024-01-25","cited_by_count":32,"area":null},{"id":"2209.13569","title":"Exploring Low Rank Training of Deep Neural Networks","created":"2022-09-27","cited_by_count":30,"area":null},{"id":"2406.04101","title":"How Far Can We Compress Instant-NGP-Based NeRF?","created":"2024-06-06","cited_by_count":30,"area":null},{"id":"2104.02244","title":"Content-Aware GAN Compression","created":"2021-04-06","cited_by_count":28,"area":null},{"id":"2502.10940","title":"CoLA: Compute-Efficient Pre-Training of LLMs via Low-Rank Activation","created":"2025-02-16","cited_by_count":28,"area":null},{"id":"2203.05483","title":"projUNN: efficient method for training deep networks with unitary matrices","created":"2022-03-10","cited_by_count":27,"area":null},{"id":"2101.09048","title":"Selfish Sparse RNN Training","created":"2021-01-22","cited_by_count":26,"area":null},{"id":"2406.04112","title":"Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation","created":"2024-06-06","cited_by_count":26,"area":null},{"id":"2109.12338","title":"Distribution-sensitive Information Retention for Accurate Binary Neural Network","created":"2021-09-25","cited_by_count":25,"area":null},{"id":"2305.02538","title":"Cuttlefish: Low-Rank Model Training without All the Tuning","created":"2023-05-04","cited_by_count":25,"area":null},{"id":"2309.16932","title":"Symmetry Induces Structure and Constraint of Learning","created":"2023-09-29","cited_by_count":25,"area":null},{"id":"2310.11028","title":"Matrix Compression via Randomized Low Rank and Low Precision Factorization","created":"2023-10-17","cited_by_count":25,"area":null},{"id":"2203.04940","title":"Data-Efficient Structured Pruning via Submodular Optimization","created":"2022-03-09","cited_by_count":23,"area":null},{"id":"2301.11233","title":"BiBench: Benchmarking and Analyzing Network Binarization","created":"2023-01-26","cited_by_count":22,"area":null},{"id":"2402.01799","title":"Faster and Lighter LLMs: A Survey on Current Challenges and Way Forward","created":"2024-02-02","cited_by_count":21,"area":null},{"id":"2405.13952","title":"Spectral Adapter: Fine-Tuning in Spectral Space","created":"2024-05-22","cited_by_count":21,"area":null},{"id":"2209.08554","title":"Pruning Neural Networks via Coresets and Convex Geometry: Towards No Assumptions","created":"2022-09-18","cited_by_count":20,"area":null},{"id":"2302.03213","title":"LUT-NN: Empower Efficient Neural Network Inference with Centroid Learning and Table Lookup","created":"2023-02-07","cited_by_count":20,"area":null},{"id":"2102.07804","title":"Scaling Up Exact Neural Network Compression by ReLU Stability","created":"2021-02-15","cited_by_count":19,"area":null},{"id":"2102.07981","title":"SiMaN: Sign-to-Magnitude Network Binarization","created":"2021-02-16","cited_by_count":18,"area":null},{"id":"2102.10212","title":"Hard-Attention for Scalable Image Classification","created":"2021-02-20","cited_by_count":18,"area":null},{"id":"2106.02694","title":"Efficient Classification of Very Large Images with Tiny Objects","created":"2021-06-04","cited_by_count":17,"area":null},{"id":"2110.15156","title":"Blending Anti-Aliasing into Vision Transformer","created":"2021-10-28","cited_by_count":16,"area":null},{"id":"2111.01673","title":"Relational Self-Attention: What's Missing in Attention for Video Understanding","created":"2021-11-02","cited_by_count":15,"area":null},{"id":"2201.03297","title":"GhostNets on Heterogeneous Devices via Cheap Operations","created":"2022-01-10","cited_by_count":15,"area":null},{"id":"2405.14377","title":"CoMERA: Computing- and Memory-Efficient Training via Rank-Adaptive Tensor Optimization","created":"2024-05-23","cited_by_count":15,"area":null},{"id":"2107.02306","title":"Connectivity Matters: Neural Network Pruning Through the Lens of Effective Sparsity","created":"2021-07-05","cited_by_count":14,"area":null},{"id":"2304.14271","title":"A Survey on Approximate Edge AI for Energy Efficient Autonomous Driving Services","created":"2023-04-13","cited_by_count":14,"area":null},{"id":"2308.13998","title":"Computation-efficient Deep Learning for Computer Vision: A Survey","created":"2023-08-27","cited_by_count":14,"area":null},{"id":"2203.10135","title":"Learning Compressed Embeddings for On-Device Inference","created":"2022-03-18","cited_by_count":13,"area":null},{"id":"2208.13141","title":"Federated Learning of Large Models at the Edge via Principal Sub-Model Training","created":"2022-08-28","cited_by_count":13,"area":null},{"id":"2108.12931","title":"NeuroCartography: Scalable Automatic Visual Summarization of Concepts in Deep Neural Networks","created":"2021-08-29","cited_by_count":12,"area":null},{"id":"2109.05221","title":"Convolutional Hough Matching Networks for Robust and Efficient Visual Correspondence","created":"2021-09-11","cited_by_count":12,"area":null},{"id":"2111.07964","title":"Deep Network Approximation in Terms of Intrinsic Parameters","created":"2021-11-15","cited_by_count":12,"area":null},{"id":"2107.04386","title":"Joint Matrix Decomposition for Deep Convolutional Neural Networks Compression","created":"2021-07-09","cited_by_count":10,"area":null},{"id":"2105.14070","title":"Accelerating Neural ODEs Using Model Order Reduction","created":"2021-05-28","cited_by_count":9,"area":null},{"id":"2107.14444","title":"Manipulating Identical Filter Redundancy for Efficient Pruning on Deep and Complicated CNN","created":"2021-07-30","cited_by_count":9,"area":null},{"id":"2108.00065","title":"Model Preserving Compression for Neural Networks","created":"2021-07-30","cited_by_count":9,"area":null},{"id":"2305.18163","title":"Compact Real-time Radiance Fields with Neural Codebook","created":"2023-05-29","cited_by_count":9,"area":null},{"id":"2510.03358","title":"Understanding Transformers for Time Series: Rank Structure, Flow-of-ranks, and Compressibility","created":"2025-10-02","cited_by_count":9,"area":null},{"id":"2111.00160","title":"DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models","created":"2021-10-30","cited_by_count":8,"area":null},{"id":"2204.05899","title":"VisCUIT: Visual Auditor for Bias in CNN Image Classifier","created":"2022-04-12","cited_by_count":8,"area":null},{"id":"2208.05788","title":"Semantic Self-adaptation: Enhancing Generalization with a Single Sample","created":"2022-08-10","cited_by_count":8,"area":null},{"id":"2308.14929","title":"Maestro: Uncovering Low-Rank Structures via Trainable Decomposition","created":"2023-08-28","cited_by_count":8,"area":null},{"id":"2309.15467","title":"Enabling Resource-efficient AIoT System with Cross-level Optimization: A survey","created":"2023-09-27","cited_by_count":8,"area":null},{"id":"2502.17788","title":"On-device edge learning for IoT data streams: a survey","created":"2025-02-25","cited_by_count":8,"area":null},{"id":"2602.02848","title":"Zero Sum SVD: Balancing Loss Sensitivity for Low Rank LLM Compression","created":"2026-02-02","cited_by_count":8,"area":null},{"id":"2102.00160","title":"Deep Model Compression based on the Training History","created":"2021-01-30","cited_by_count":7,"area":null},{"id":"2202.10716","title":"HRel: Filter Pruning based on High Relevance between Activation Maps and Class Labels","created":"2022-02-22","cited_by_count":7,"area":null},{"id":"2206.08605","title":"On Efficient Real-Time Semantic Segmentation: A Survey","created":"2022-06-17","cited_by_count":7,"area":null},{"id":"2209.15529","title":"TT-NF: Tensor Train Neural Fields","created":"2022-09-30","cited_by_count":7,"area":null},{"id":"2406.17887","title":"Federated Dynamical Low-Rank Training with Global Loss Convergence Guarantees","created":"2024-06-25","cited_by_count":7,"area":null},{"id":"2410.17397","title":"Quantum Large Language Models via Tensor Network Disentanglers","created":"2024-10-22","cited_by_count":7,"area":null},{"id":"2604.02119","title":"AA-SVD : Anchored and Adaptive SVD for Large Language Model Compression","created":"2026-04-02","cited_by_count":7,"area":null},{"id":"2103.10858","title":"Toward Compact Deep Neural Networks via Energy-Aware Pruning","created":"2021-03-19","cited_by_count":6,"area":null},{"id":"2103.11083","title":"Compacting Deep Neural Networks for Internet of Things: Methods and Applications","created":"2021-03-20","cited_by_count":6,"area":null},{"id":"2202.01290","title":"Cyclical Pruning for Sparse Neural Networks","created":"2022-02-02","cited_by_count":6,"area":null},{"id":"2203.04516","title":"Update Compression for Deep Neural Networks on the Edge","created":"2022-03-09","cited_by_count":6,"area":null},{"id":"2304.05440","title":"PixelRNN: In-pixel Recurrent Neural Networks for End-to-end-optimized Perception with Neural Sensors","created":"2023-04-11","cited_by_count":6,"area":null},{"id":"2407.01320","title":"Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuning","created":"2024-07-01","cited_by_count":6,"area":null},{"id":"2409.07787","title":"Stable Language Model Pre-training by Reducing Embedding Variability","created":"2024-09-12","cited_by_count":6,"area":null},{"id":"2409.18850","title":"Two Sparse Matrices are Better than One: Sparsifying Neural Networks with Double Sparse Factorization","created":"2024-09-27","cited_by_count":6,"area":null},{"id":"2411.02063","title":"Scalable Efficient Training of Large Language Models with Low-dimensional Projected Attention","created":"2024-11-04","cited_by_count":6,"area":null},{"id":"2505.21732","title":"LaX: Boosting Low-Rank Training of Foundation Models via Latent Crossing","created":"2025-05-27","cited_by_count":6,"area":null},{"id":"2107.06916","title":"Training Compact CNNs for Image Classification using Dynamic-coded Filter Fusion","created":"2021-07-14","cited_by_count":5,"area":null},{"id":"2112.11438","title":"Mixed Precision Low-bit Quantization of Neural Network Language Models for Speech Recognition","created":"2021-11-29","cited_by_count":5,"area":null},{"id":"2303.13635","title":"Low Rank Optimization for Efficient Deep Learning: Making A Balance between Compact Architecture and Fast Training","created":"2023-03-22","cited_by_count":5,"area":null},{"id":"2310.11611","title":"In defense of parameter sharing for model-compression","created":"2023-10-17","cited_by_count":5,"area":null},{"id":"2101.04073","title":"Deeplite Neutrino: An End-to-End Framework for Constrained Deep Learning Model Optimization","created":"2021-01-11","cited_by_count":4,"area":null},{"id":"2207.11577","title":"Augmented Bilinear Network for Incremental Multi-Stock Time-Series Classification","created":"2022-07-23","cited_by_count":4,"area":null},{"id":"2301.11360","title":"The Power of Linear Combinations: Learning with Random Convolutions","created":"2023-01-26","cited_by_count":4,"area":null},{"id":"2302.07612","title":"Towards Optimal Compression: Joint Pruning and Quantization","created":"2023-02-15","cited_by_count":4,"area":null}],"next_cursor":"100"}