{"total":53,"rows":[{"id":"2312.13558","title":"The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction","created":"2023-12-21","cited_by_count":123,"area":"lr"},{"id":"2105.01029","title":"Initialization and Regularization of Factorized Neural Layers","created":"2021-05-03","cited_by_count":58,"area":"distill"},{"id":"2503.06027","title":"Empowering Edge Intelligence: A Comprehensive Survey on On-Device AI Models","created":"2025-03-08","cited_by_count":46,"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":"2505.11497","title":"QVGen: Pushing the Limit of Quantized Video Generative Models","created":"2025-05-16","cited_by_count":22,"area":"diffusion"},{"id":"2308.00310","title":"GradOrth: A Simple yet Efficient Out-of-Distribution Detection with Orthogonal Projection of Gradients","created":"2023-08-01","cited_by_count":21,"area":null},{"id":"2509.24882","title":"Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning Regime","created":"2025-09-29","cited_by_count":20,"area":null},{"id":"2507.17343","title":"Principled Multimodal Representation Learning","created":"2025-07-23","cited_by_count":19,"area":null},{"id":"2205.11921","title":"Compression-aware Training of Neural Networks using Frank-Wolfe","created":"2022-05-24","cited_by_count":16,"area":null},{"id":"2306.01485","title":"Robust low-rank training via approximate orthonormal constraints","created":"2023-06-02","cited_by_count":13,"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":"2401.10341","title":"ELRT: Efficient Low-Rank Training for Compact Convolutional Neural Networks","created":"2024-01-18","cited_by_count":11,"area":null},{"id":"2306.11250","title":"InRank: Incremental Low-Rank Learning","created":"2023-06-20","cited_by_count":10,"area":null},{"id":"2310.10700","title":"PELA: Learning Parameter-Efficient Models with Low-Rank Approximation","created":"2023-10-16","cited_by_count":9,"area":null},{"id":"2310.14809","title":"Learning spatio-temporal patterns with Neural Cellular Automata","created":"2023-10-23","cited_by_count":8,"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":"2505.08022","title":"Dynamical Low-Rank Compression of Neural Networks with Robustness under Adversarial Attacks","created":"2025-05-12","cited_by_count":6,"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":"2310.03165","title":"Enhancing Accuracy in Deep Learning Using Random Matrix Theory","created":"2023-10-04","cited_by_count":5,"area":null},{"id":"2212.01957","title":"CSTAR: Towards Compact and STructured Deep Neural Networks with Adversarial Robustness","created":"2022-12-04","cited_by_count":4,"area":null},{"id":"2306.02433","title":"Riemannian Low-Rank Model Compression for Federated Learning with Over-the-Air Aggregation","created":"2023-06-04","cited_by_count":4,"area":null},{"id":"2412.06868","title":"Compression for Better: A General and Stable Lossless Compression Framework","created":"2024-12-09","cited_by_count":4,"area":null},{"id":"2108.11430","title":"Towards Memory-Efficient Neural Networks via Multi-Level in situ Generation","created":"2021-08-25","cited_by_count":3,"area":null},{"id":"2204.05566","title":"Compact Model Training by Low-Rank Projection with Energy Transfer","created":"2022-04-12","cited_by_count":3,"area":null},{"id":"2406.13225","title":"Communication-Efficient Federated Knowledge Graph Embedding with Entity-Wise Top-K Sparsification","created":"2024-06-19","cited_by_count":3,"area":null},{"id":"2412.06867","title":"Lossless Model Compression via Joint Low-Rank Factorization Optimization","created":"2024-12-09","cited_by_count":3,"area":null},{"id":"2303.08986","title":"Deep Learning Weight Pruning with RMT-SVD: Increasing Accuracy and Reducing Overfitting","created":"2023-03-15","cited_by_count":2,"area":null},{"id":"2406.16450","title":"Building on Efficient Foundations: Effectively Training LLMs with Structured Feedforward Layers","created":"2024-06-24","cited_by_count":2,"area":null},{"id":"2503.12211","title":"Changing Base Without Losing Pace: A GPU-Efficient Alternative to MatMul in DNNs","created":"2025-03-15","cited_by_count":2,"area":null},{"id":"2509.25136","title":"BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2310.02776","title":"Dynamic Shuffle: An Efficient Channel Mixture Method","created":"2023-10-04","cited_by_count":1,"area":null},{"id":"2311.11093","title":"Flat Minima in Linear Estimation and an Extended Gauss Markov Theorem","created":"2023-11-18","cited_by_count":1,"area":null},{"id":"2407.03442","title":"Fisher-aware Quantization for DETR Detectors with Critical-category Objectives","created":"2024-07-03","cited_by_count":1,"area":null},{"id":"2506.01869","title":"Frugal Machine Learning for Energy-efficient, and Resource-aware Artificial Intelligence","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2510.25594","title":"Feedback Alignment Meets Low-Rank Manifolds: A Structured Recipe for Local Learning","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2511.04485","title":"Q3R: Quadratic Reweighted Rank Regularizer for Effective Low-Rank Training","created":"2025-11-06","cited_by_count":1,"area":null},{"id":"2602.06476","title":"Prism: Spectral Parameter Sharing for Multi-Agent Reinforcement Learning","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2602.09509","title":"Beyond Student: An Asymmetric Network for Neural Network Inheritance","created":"2026-02-10","cited_by_count":1,"area":"distill"},{"id":"2607.08754","title":"SLORR: Simple and Efficient In-Training Low-Rank Regularization","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2108.02893","title":"Basis Scaling and Double Pruning for Efficient Inference in Network-Based Transfer Learning","created":"2021-08-06","cited_by_count":0,"area":null},{"id":"2112.05705","title":"Pruning Pretrained Encoders with a Multitask Objective","created":"2021-12-10","cited_by_count":0,"area":null},{"id":"2210.08415","title":"Stability of Accuracy for the Training of DNNs Via the Uniform Doubling Condition","created":"2022-10-16","cited_by_count":0,"area":null},{"id":"2306.09822","title":"Lightweight Attribute Localizing Models for Pedestrian Attribute Recognition","created":"2023-06-16","cited_by_count":0,"area":null},{"id":"2401.08014","title":"Convolutional Neural Network Compression via Dynamic Parameter Rank Pruning","created":"2024-01-15","cited_by_count":0,"area":null},{"id":"2405.01067","title":"AB-Training: A Communication-Efficient Approach for Distributed Low-Rank Learning","created":"2024-05-02","cited_by_count":0,"area":null},{"id":"2408.00923","title":"Reclaiming Residual Knowledge: A Novel Paradigm to Low-Bit Quantization","created":"2024-08-01","cited_by_count":0,"area":null},{"id":"2408.16289","title":"Convolutional Neural Network Compression Based on Low-Rank Decomposition","created":"2024-08-29","cited_by_count":0,"area":null},{"id":"2504.03037","title":"Low Rank Factorizations are Indirect Encodings for Deep Neuroevolution","created":"2025-04-03","cited_by_count":0,"area":"deeprl"},{"id":"2506.20152","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","created":"2025-06-25","cited_by_count":0,"area":null},{"id":"2604.00733","title":"Spectral Compact Training: Pre-Training Large Language Models via Permanent Truncated SVD and Stiefel QR Retraction","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2605.28573","title":"Efficient Pre-Training of LLMs through Truncated SVD Representations","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2609.32615","title":"Stabilizing the Dynamic Low-Rank Training","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}