{"total":207,"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":"2412.00081","title":"Task Singular Vectors: Reducing Task Interference in Model Merging","created":"2024-11-26","cited_by_count":147,"area":null},{"id":"2210.06707","title":"Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformer","created":"2022-10-13","cited_by_count":108,"area":null},{"id":"2110.13100","title":"Parameter Prediction for Unseen Deep Architectures","created":"2021-10-25","cited_by_count":89,"area":null},{"id":"2406.13155","title":"Convolutional Kolmogorov-Arnold Networks","created":"2024-06-19","cited_by_count":77,"area":null},{"id":"2307.02129","title":"How Deep Neural Networks Learn Compositional Data: The Random Hierarchy Model","created":"2023-07-05","cited_by_count":71,"area":null},{"id":"2210.04092","title":"Advancing Model Pruning via Bi-level Optimization","created":"2022-10-08","cited_by_count":56,"area":null},{"id":"2106.04217","title":"Dynamic Sparse Training for Deep Reinforcement Learning","created":"2021-06-08","cited_by_count":49,"area":null},{"id":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"area":null},{"id":"2301.06568","title":"Ankh: Optimized Protein Language Model Unlocks General-Purpose Modelling","created":"2023-01-16","cited_by_count":45,"area":null},{"id":"2205.05996","title":"Blueprint Separable Residual Network for Efficient Image Super-Resolution","created":"2022-05-12","cited_by_count":44,"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":"2209.14764","title":"Model Zoos: A Dataset of Diverse Populations of Neural Network Models","created":"2022-09-29","cited_by_count":39,"area":null},{"id":"2402.18153","title":"Diffusion-Based Neural Network Weights Generation","created":"2024-02-28","cited_by_count":39,"area":null},{"id":"2406.01775","title":"OLoRA: Orthonormal Low-Rank Adaptation of Large Language Models","created":"2024-06-03","cited_by_count":39,"area":null},{"id":"2209.05310","title":"On the Factory Floor: ML Engineering for Industrial-Scale Ads Recommendation Models","created":"2022-09-12","cited_by_count":34,"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":"2304.00145","title":"Directional Connectivity-based Segmentation of Medical Images","created":"2023-03-31","cited_by_count":30,"area":null},{"id":"2102.13229","title":"Consistent Sparse Deep Learning: Theory and Computation","created":"2021-02-25","cited_by_count":27,"area":null},{"id":"2309.03160","title":"ResFields: Residual Neural Fields for Spatiotemporal Signals","created":"2023-09-06","cited_by_count":27,"area":null},{"id":"2105.04504","title":"Deep Neural Networks as Point Estimates for Deep Gaussian Processes","created":"2021-05-10","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":"2304.00253","title":"Q-DETR: An Efficient Low-Bit Quantized Detection Transformer","created":"2023-04-01","cited_by_count":24,"area":null},{"id":"2203.04940","title":"Data-Efficient Structured Pruning via Submodular Optimization","created":"2022-03-09","cited_by_count":23,"area":null},{"id":"2102.07156","title":"ChipNet: Budget-Aware Pruning with Heaviside Continuous Approximations","created":"2021-02-14","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":"2104.13424","title":"Policy Manifold Search: Exploring the Manifold Hypothesis for Diversity-based Neuroevolution","created":"2021-04-27","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":"2305.18512","title":"A Rainbow in Deep Network Black Boxes","created":"2023-05-29","cited_by_count":18,"area":null},{"id":"2308.04466","title":"Backdoor Federated Learning by Poisoning Backdoor-Critical Layers","created":"2023-08-08","cited_by_count":18,"area":null},{"id":"2106.02923","title":"Local Disentanglement in Variational Auto-Encoders Using Jacobian $L_1$ Regularization","created":"2021-06-05","cited_by_count":17,"area":null},{"id":"2102.01732","title":"Truly Sparse Neural Networks at Scale","created":"2021-02-02","cited_by_count":16,"area":null},{"id":"2207.01982","title":"Defending against the Label-flipping Attack in Federated Learning","created":"2022-07-05","cited_by_count":16,"area":null},{"id":"2109.04236","title":"ECQ$^{\\text{x}}$: Explainability-Driven Quantization for Low-Bit and Sparse DNNs","created":"2021-09-09","cited_by_count":15,"area":null},{"id":"2207.00872","title":"FL-Defender: Combating Targeted Attacks in Federated Learning","created":"2022-07-02","cited_by_count":15,"area":null},{"id":"2306.03445","title":"MetaGait: Learning to Learn an Omni Sample Adaptive Representation for Gait Recognition","created":"2023-06-06","cited_by_count":15,"area":null},{"id":"2104.11939","title":"Piggyback GAN: Efficient Lifelong Learning for Image Conditioned Generation","created":"2021-04-24","cited_by_count":14,"area":null},{"id":"2109.14710","title":"Convolutional Neural Network Compression through Generalized Kronecker Product Decomposition","created":"2021-09-29","cited_by_count":14,"area":null},{"id":"2110.05667","title":"Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Pruned Neural Networks","created":"2021-10-12","cited_by_count":14,"area":null},{"id":"2112.06126","title":"Neural Network Quantization for Efficient Inference: A Survey","created":"2021-12-08","cited_by_count":14,"area":null},{"id":"2304.13539","title":"Tensor Decomposition for Model Reduction in Neural Networks: A Review","created":"2023-04-26","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":"2107.08982","title":"InsPose: Instance-Aware Networks for Single-Stage Multi-Person Pose Estimation","created":"2021-07-19","cited_by_count":13,"area":null},{"id":"2203.10135","title":"Learning Compressed Embeddings for On-Device Inference","created":"2022-03-18","cited_by_count":13,"area":null},{"id":"2305.12354","title":"Bi-ViT: Pushing the Limit of Vision Transformer Quantization","created":"2023-05-21","cited_by_count":13,"area":null},{"id":"2209.01542","title":"Recurrent Bilinear Optimization for Binary Neural Networks","created":"2022-09-04","cited_by_count":12,"area":null},{"id":"2305.19059","title":"Geometry-aware training of factorized layers in tensor Tucker format","created":"2023-05-30","cited_by_count":12,"area":null},{"id":"2201.08050","title":"TerViT: An Efficient Ternary Vision Transformer","created":"2022-01-20","cited_by_count":11,"area":null},{"id":"2506.13771","title":"LittleBit: Ultra Low-Bit Quantization via Latent Factorization","created":"2025-05-30","cited_by_count":11,"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":"2210.14672","title":"Sparsity in Continuous-Depth Neural Networks","created":"2022-10-26","cited_by_count":10,"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":"2112.15139","title":"Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural Networks","created":"2021-12-30","cited_by_count":9,"area":null},{"id":"2206.02976","title":"Recall Distortion in Neural Network Pruning and the Undecayed Pruning Algorithm","created":"2022-06-07","cited_by_count":9,"area":null},{"id":"2208.02235","title":"Quantum-Inspired Tensor Neural Networks for Partial Differential Equations","created":"2022-08-03","cited_by_count":9,"area":null},{"id":"2311.11883","title":"Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review","created":"2023-11-20","cited_by_count":9,"area":null},{"id":"2407.00676","title":"Instruct-IPT: All-in-One Image Processing Transformer via Weight Modulation","created":"2024-06-30","cited_by_count":9,"area":null},{"id":"2501.06357","title":"Mix-QViT: Mixed-Precision Vision Transformer Quantization Driven by Layer Importance and Quantization Sensitivity","created":"2025-01-10","cited_by_count":9,"area":null},{"id":"2503.22178","title":"AdaRank: Adaptive Rank Pruning for Enhanced Model Merging","created":"2025-03-28","cited_by_count":9,"area":null},{"id":"2510.24966","title":"Sequences of Logits Reveal the Low Rank Structure of Language Models","created":"2025-10-28","cited_by_count":9,"area":null},{"id":"2102.06599","title":"Neural Architecture Search as Program Transformation Exploration","created":"2021-02-12","cited_by_count":8,"area":null},{"id":"2110.04350","title":"FRL: Federated Rank Learning","created":"2021-10-08","cited_by_count":8,"area":null},{"id":"2110.05329","title":"Avoiding Forgetting and Allowing Forward Transfer in Continual Learning via Sparse Networks","created":"2021-10-11","cited_by_count":8,"area":null},{"id":"2301.07966","title":"Getting Away with More Network Pruning: From Sparsity to Geometry and Linear Regions","created":"2023-01-19","cited_by_count":8,"area":null},{"id":"2401.11243","title":"LRP-QViT: Mixed-Precision Vision Transformer Quantization via Layer-wise Relevance Propagation","created":"2024-01-20","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":"2205.03824","title":"A Survey on AI Sustainability: Emerging Trends on Learning Algorithms and Research Challenges","created":"2022-05-08","cited_by_count":7,"area":null},{"id":"2304.09876","title":"Model Pruning Enables Localized and Efficient Federated Learning for Yield Forecasting and Data Sharing","created":"2023-04-19","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":"2103.11083","title":"Compacting Deep Neural Networks for Internet of Things: Methods and Applications","created":"2021-03-20","cited_by_count":6,"area":null},{"id":"2112.03690","title":"Low-rank Tensor Decomposition for Compression of Convolutional Neural Networks Using Funnel Regularization","created":"2021-12-07","cited_by_count":6,"area":null},{"id":"2312.11973","title":"Continual Learning: Forget-free Winning Subnetworks for Video Representations","created":"2023-12-19","cited_by_count":6,"area":null},{"id":"2407.09835","title":"Investigating Low-Rank Training in Transformer Language Models: Efficiency and Scaling Analysis","created":"2024-07-13","cited_by_count":6,"area":null},{"id":"2107.06825","title":"A Generalized Lottery Ticket Hypothesis","created":"2021-07-03","cited_by_count":5,"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":"2108.10808","title":"Greenformers: Improving Computation and Memory Efficiency in Transformer Models via Low-Rank Approximation","created":"2021-08-24","cited_by_count":5,"area":null},{"id":"2301.06132","title":"Deep Diversity-Enhanced Feature Representation of Hyperspectral Images","created":"2023-01-15","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":"2303.14962","title":"Forget-free Continual Learning with Soft-Winning SubNetworks","created":"2023-03-27","cited_by_count":5,"area":null},{"id":"2304.02319","title":"Efficient CNNs via Passive Filter Pruning","created":"2023-04-05","cited_by_count":5,"area":null},{"id":"2309.01627","title":"Cross-Consistent Deep Unfolding Network for Adaptive All-In-One Video Restoration","created":"2023-09-04","cited_by_count":5,"area":null},{"id":"2508.04581","title":"Share Your Attention: Transformer Weight Sharing via Matrix-based Dictionary Learning","created":"2025-08-06","cited_by_count":5,"area":null},{"id":"2510.12077","title":"Compressibility Measures Complexity: Minimum Description Length Meets Singular Learning Theory","created":"2025-10-14","cited_by_count":5,"area":null},{"id":"2109.05075","title":"On the Compression of Neural Networks Using $\\ell_0$-Norm Regularization and Weight Pruning","created":"2021-09-10","cited_by_count":4,"area":null},{"id":"2110.00214","title":"Spiking Hyperdimensional Network: Neuromorphic Models Integrated with Memory-Inspired Framework","created":"2021-10-01","cited_by_count":4,"area":null},{"id":"2111.08577","title":"Neuron-based Pruning of Deep Neural Networks with Better Generalization using Kronecker Factored Curvature Approximation","created":"2021-11-16","cited_by_count":4,"area":null},{"id":"2201.11103","title":"Auto-Compressing Subset Pruning for Semantic Image Segmentation","created":"2022-01-26","cited_by_count":4,"area":null},{"id":"2202.10728","title":"Distilled Neural Networks for Efficient Learning to Rank","created":"2022-02-22","cited_by_count":4,"area":null},{"id":"2212.13970","title":"Breaking the Architecture Barrier: A Method for Efficient Knowledge Transfer Across Networks","created":"2022-12-28","cited_by_count":4,"area":null},{"id":"2302.08571","title":"A Comprehensive Review and a Taxonomy of Edge Machine Learning: Requirements, Paradigms, and Techniques","created":"2023-02-16","cited_by_count":4,"area":null},{"id":"2304.13718","title":"Sparsified Model Zoo Twins: Investigating Populations of Sparsified Neural Network Models","created":"2023-04-26","cited_by_count":4,"area":null},{"id":"2305.18665","title":"E-PANNs: Sound Recognition Using Efficient Pre-trained Audio Neural Networks","created":"2023-05-30","cited_by_count":4,"area":null},{"id":"2410.02147","title":"Efficient Source-Free Time-Series Adaptation via Parameter Subspace Disentanglement","created":"2024-10-03","cited_by_count":4,"area":null},{"id":"2503.08976","title":"Not All Edges are Equally Robust: Evaluating the Robustness of Ranking-Based Federated Learning","created":"2025-03-12","cited_by_count":4,"area":null},{"id":"2603.03597","title":"NuMuon: Nuclear-Norm-Constrained Muon for Compressible LLM Training","created":"2026-03-04","cited_by_count":4,"area":null},{"id":"2105.10832","title":"Spectral Pruning for Recurrent Neural Networks","created":"2021-05-23","cited_by_count":3,"area":null},{"id":"2110.00684","title":"Learning Compact Representations of Neural Networks using DiscriminAtive Masking (DAM)","created":"2021-10-01","cited_by_count":3,"area":null},{"id":"2202.02248","title":"Backpropagation Neural Tree","created":"2022-02-04","cited_by_count":3,"area":null}],"next_cursor":"100"}