{"total":250,"rows":[{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202,"area":null},{"id":"2202.07800","title":"Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations","created":"2022-02-16","cited_by_count":363,"area":null},{"id":"2101.10423","title":"Online Continual Learning in Image Classification: An Empirical Survey","created":"2021-01-25","cited_by_count":245,"area":null},{"id":"2212.05055","title":"Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints","created":"2022-12-09","cited_by_count":209,"area":"moe"},{"id":"2501.18427","title":"SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer","created":"2025-01-30","cited_by_count":165,"area":"lr"},{"id":"2301.08727","title":"Neural Architecture Search: Insights from 1000 Papers","created":"2023-01-20","cited_by_count":139,"area":null},{"id":"2110.07298","title":"LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5","created":"2021-10-14","cited_by_count":104,"area":null},{"id":"2303.00980","title":"Learning to Grow Pretrained Models for Efficient Transformer Training","created":"2023-03-02","cited_by_count":83,"area":null},{"id":"2101.01341","title":"Practical Blind Membership Inference Attack via Differential Comparisons","created":"2021-01-05","cited_by_count":78,"area":"safety"},{"id":"2111.06719","title":"On Transferability of Prompt Tuning for Natural Language Processing","created":"2021-11-12","cited_by_count":75,"area":null},{"id":"2305.15555","title":"Deep Reinforcement Learning with Plasticity Injection","created":"2023-05-24","cited_by_count":74,"area":null},{"id":"2110.07143","title":"bert2BERT: Towards Reusable Pretrained Language Models","created":"2021-10-14","cited_by_count":70,"area":null},{"id":"2201.05125","title":"GradMax: Growing Neural Networks using Gradient Information","created":"2022-01-13","cited_by_count":66,"area":null},{"id":"2301.05792","title":"RMM: Reinforced Memory Management for Class-Incremental Learning","created":"2023-01-14","cited_by_count":66,"area":null},{"id":"2305.12281","title":"Lifelong Language Pretraining with Distribution-Specialized Experts","created":"2023-05-20","cited_by_count":66,"area":"moe"},{"id":"2205.07877","title":"A Comprehensive Survey on Model Quantization for Deep Neural Networks in Image Classification","created":"2022-05-14","cited_by_count":65,"area":null},{"id":"2206.01626","title":"Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress","created":"2022-06-03","cited_by_count":65,"area":null},{"id":"2209.14733","title":"Hyper-Representations as Generative Models: Sampling Unseen Neural Network Weights","created":"2022-09-29","cited_by_count":64,"area":"distill"},{"id":"2406.06391","title":"Towards Lifelong Learning of Large Language Models: A Survey","created":"2024-06-10","cited_by_count":64,"area":null},{"id":"2106.10207","title":"Distributed Deep Learning in Open Collaborations","created":"2021-06-18","cited_by_count":58,"area":null},{"id":"2509.01322","title":"LongCat-Flash Technical Report","created":"2025-09-01","cited_by_count":58,"area":"agents"},{"id":"2109.11369","title":"Recent Advances of Continual Learning in Computer Vision: An Overview","created":"2021-09-23","cited_by_count":55,"area":null},{"id":"2102.08574","title":"Firefly Neural Architecture Descent: a General Approach for Growing Neural Networks","created":"2021-02-17","cited_by_count":49,"area":null},{"id":"2203.06211","title":"Staged Training for Transformer Language Models","created":"2022-03-11","cited_by_count":49,"area":null},{"id":"2211.09703","title":"EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbones","created":"2022-11-17","cited_by_count":43,"area":null},{"id":"2405.15319","title":"Stacking Your Transformers: A Closer Look at Model Growth for Efficient LLM Pre-Training","created":"2024-05-24","cited_by_count":43,"area":null},{"id":"2311.18823","title":"Initializing Models with Larger Ones","created":"2023-11-30","cited_by_count":39,"area":null},{"id":"2210.06640","title":"Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2203.14509","title":"Automated Progressive Learning for Efficient Training of Vision Transformers","created":"2022-03-28","cited_by_count":37,"area":null},{"id":"2101.01926","title":"Curriculum-Meta Learning for Order-Robust Continual Relation Extraction","created":"2021-01-06","cited_by_count":34,"area":null},{"id":"2103.07492","title":"Continual Learning for Recurrent Neural Networks: an Empirical Evaluation","created":"2021-03-12","cited_by_count":34,"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":"2305.06061","title":"Visual Tuning","created":"2023-05-10","cited_by_count":34,"area":null},{"id":"2305.02869","title":"Masked Structural Growth for 2x Faster Language Model Pre-training","created":"2023-05-04","cited_by_count":33,"area":null},{"id":"2212.11696","title":"Reversible Column Networks","created":"2022-12-22","cited_by_count":32,"area":null},{"id":"2208.06974","title":"Learning Semantic Correspondence with Sparse Annotations","created":"2022-08-15","cited_by_count":31,"area":null},{"id":"2303.04143","title":"Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?","created":"2023-03-07","cited_by_count":29,"area":null},{"id":"2409.12903","title":"Scaling Smart: Accelerating Large Language Model Pre-training with Small Model Initialization","created":"2024-09-19","cited_by_count":29,"area":null},{"id":"2203.02721","title":"Consistent Representation Learning for Continual Relation Extraction","created":"2022-03-05","cited_by_count":28,"area":"distill"},{"id":"2404.18211","title":"A survey of dynamic graph neural networks","created":"2024-04-28","cited_by_count":24,"area":null},{"id":"2103.16547","title":"The Elastic Lottery Ticket Hypothesis","created":"2021-03-30","cited_by_count":23,"area":null},{"id":"2307.00360","title":"BatGPT: A Bidirectional Autoregessive Talker from Generative Pre-trained Transformer","created":"2023-07-01","cited_by_count":23,"area":null},{"id":"2310.07999","title":"LEMON: Lossless model expansion","created":"2023-10-12","cited_by_count":23,"area":"lr"},{"id":"2309.03852","title":"FLM-101B: An Open LLM and How to Train It with $100K Budget","created":"2023-09-07","cited_by_count":22,"area":null},{"id":"2401.02731","title":"Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks","created":"2024-01-05","cited_by_count":22,"area":"moe"},{"id":"2104.09396","title":"Continual Learning in Sensor-based Human Activity Recognition: an Empirical Benchmark Analysis","created":"2021-04-19","cited_by_count":21,"area":null},{"id":"2109.14536","title":"PINNup: Robust neural network wavefield solutions using frequency upscaling and neuron splitting","created":"2021-09-29","cited_by_count":20,"area":null},{"id":"2105.01015","title":"Bag of Baselines for Multi-objective Joint Neural Architecture Search and Hyperparameter Optimization","created":"2021-05-03","cited_by_count":19,"area":null},{"id":"2212.00824","title":"On-device Training: A First Overview on Existing Systems","created":"2022-12-01","cited_by_count":19,"area":null},{"id":"2409.19044","title":"On the Inductive Bias of Stacking Towards Improving Reasoning","created":"2024-09-27","cited_by_count":19,"area":"lr"},{"id":"2202.08539","title":"When, where, and how to add new neurons to ANNs","created":"2022-02-17","cited_by_count":18,"area":null},{"id":"2204.07554","title":"Efficient Architecture Search for Diverse Tasks","created":"2022-04-15","cited_by_count":18,"area":null},{"id":"2405.08768","title":"EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Training","created":"2024-05-14","cited_by_count":18,"area":null},{"id":"2102.10301","title":"Towards Accurate and Compact Architectures via Neural Architecture Transformer","created":"2021-02-20","cited_by_count":17,"area":null},{"id":"2203.02135","title":"Continual Few-shot Relation Learning via Embedding Space Regularization and Data Augmentation","created":"2022-03-04","cited_by_count":17,"area":null},{"id":"2309.14763","title":"ConPET: Continual Parameter-Efficient Tuning for Large Language Models","created":"2023-09-26","cited_by_count":17,"area":null},{"id":"2310.11451","title":"Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspective","created":"2023-10-17","cited_by_count":17,"area":null},{"id":"2406.17503","title":"WAVE: Weight Templates for Adaptive Initialization of Variable-sized Models","created":"2024-06-25","cited_by_count":17,"area":null},{"id":"2205.12755","title":"An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems","created":"2022-05-25","cited_by_count":16,"area":null},{"id":"2112.04467","title":"CoMPS: Continual Meta Policy Search","created":"2021-12-08","cited_by_count":15,"area":null},{"id":"2310.10699","title":"Reusing Pretrained Models by Multi-linear Operators for Efficient Training","created":"2023-10-16","cited_by_count":15,"area":null},{"id":"2207.02375","title":"3DG-STFM: 3D Geometric Guided Student-Teacher Feature Matching","created":"2022-07-06","cited_by_count":14,"area":null},{"id":"2307.04526","title":"Self-Expanding Neural Networks","created":"2023-07-10","cited_by_count":14,"area":null},{"id":"2112.09245","title":"Automated Deep Learning: Neural Architecture Search Is Not the End","created":"2021-12-16","cited_by_count":13,"area":null},{"id":"2308.06103","title":"Composable Function-preserving Expansions for Transformer Architectures","created":"2023-08-11","cited_by_count":13,"area":null},{"id":"2309.06799","title":"When Geoscience Meets Foundation Models: Towards General Geoscience Artificial Intelligence System","created":"2023-09-13","cited_by_count":13,"area":null},{"id":"2502.03009","title":"Scaling Laws for Upcycling Mixture-of-Experts Language Models","created":"2025-02-05","cited_by_count":13,"area":"moe"},{"id":"2505.05587","title":"Steepest Descent Density Control for Compact 3D Gaussian Splatting","created":"2025-05-08","cited_by_count":13,"area":null},{"id":"2206.01520","title":"A Survey on Computationally Efficient Neural Architecture Search","created":"2022-06-03","cited_by_count":12,"area":null},{"id":"2312.14227","title":"ElasticTrainer: Speeding Up On-Device Training with Runtime Elastic Tensor Selection","created":"2023-12-21","cited_by_count":12,"area":null},{"id":"2106.07172","title":"Energy-efficient Knowledge Distillation for Spiking Neural Networks","created":"2021-06-14","cited_by_count":11,"area":"distill"},{"id":"2407.02783","title":"52B to 1T: Lessons Learned via Tele-FLM Series","created":"2024-07-03","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":"2211.01778","title":"Progressive Transformation Learning for Leveraging Virtual Images in Training","created":"2022-11-03","cited_by_count":10,"area":null},{"id":"2310.09886","title":"Lifelong Sequence Generation with Dynamic Module Expansion and Adaptation","created":"2023-10-15","cited_by_count":10,"area":null},{"id":"2401.09192","title":"Preparing Lessons for Progressive Training on Language Models","created":"2024-01-17","cited_by_count":10,"area":null},{"id":"2402.05913","title":"Efficient Stagewise Pretraining via Progressive Subnetworks","created":"2024-02-08","cited_by_count":10,"area":null},{"id":"2405.14132","title":"Text-to-Model: Text-Conditioned Neural Network Diffusion for Train-Once-for-All Personalization","created":"2024-05-23","cited_by_count":10,"area":"diffusion"},{"id":"2407.11030","title":"DLO: Dynamic Layer Operation for Efficient Vertical Scaling of LLMs","created":"2024-07-03","cited_by_count":10,"area":"moe"},{"id":"2107.11496","title":"Training multi-objective/multi-task collocation physics-informed neural network with student/teachers transfer learnings","created":"2021-07-24","cited_by_count":9,"area":null},{"id":"2110.15538","title":"On Cross-Layer Alignment for Model Fusion of Heterogeneous Neural Networks","created":"2021-10-29","cited_by_count":9,"area":"distill"},{"id":"2209.07326","title":"A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems","created":"2022-09-15","cited_by_count":9,"area":null},{"id":"2305.18239","title":"A Study on Knowledge Distillation from Weak Teacher for Scaling Up Pre-trained Language Models","created":"2023-05-26","cited_by_count":9,"area":"distill"},{"id":"2307.02588","title":"TransformerG2G: Adaptive time-stepping for learning temporal graph embeddings using transformers","created":"2023-07-05","cited_by_count":9,"area":null},{"id":"2402.12035","title":"Class-incremental Learning for Time Series: Benchmark and Evaluation","created":"2024-02-19","cited_by_count":9,"area":null},{"id":"2405.19816","title":"Growing Tiny Networks: Spotting Expressivity Bottlenecks and Fixing Them Optimally","created":"2024-05-30","cited_by_count":9,"area":null},{"id":"2410.23168","title":"TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters","created":"2024-10-30","cited_by_count":9,"area":null},{"id":"2109.13441","title":"DynG2G: An Efficient Stochastic Graph Embedding Method for Temporal Graphs","created":"2021-09-28","cited_by_count":8,"area":null},{"id":"2306.12700","title":"Accelerated Training via Incrementally Growing Neural Networks using Variance Transfer and Learning Rate Adaptation","created":"2023-06-22","cited_by_count":8,"area":null},{"id":"2110.03848","title":"Speeding up Deep Model Training by Sharing Weights and Then Unsharing","created":"2021-10-08","cited_by_count":7,"area":null},{"id":"2203.05692","title":"Lifelong Adaptive Machine Learning for Sensor-based Human Activity Recognition Using Prototypical Networks","created":"2022-03-11","cited_by_count":7,"area":null},{"id":"2311.00447","title":"On the Opportunities of Green Computing: A Survey","created":"2023-11-01","cited_by_count":7,"area":null},{"id":"2311.04251","title":"MixtureGrowth: Growing Neural Networks by Recombining Learned Parameters","created":"2023-11-07","cited_by_count":7,"area":null},{"id":"2406.06567","title":"DHA: Learning Decoupled-Head Attention from Transformer Checkpoints via Adaptive Heads Fusion","created":"2024-06-03","cited_by_count":7,"area":null},{"id":"2407.12665","title":"Beyond Next Token Prediction: Patch-Level Training for Large Language Models","created":"2024-07-17","cited_by_count":7,"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":"2602.12952","title":"Transporting Task Vectors across Different Architectures without Training","created":"2026-02-13","cited_by_count":6,"area":null},{"id":"2605.18632","title":"Position: Weight Space Should Be a First-Class Generative AI Modality","created":"2026-05-18","cited_by_count":6,"area":null},{"id":"2101.07945","title":"Beyond Fine-tuning: Classifying High Resolution Mammograms using Function-Preserving Transformations","created":"2021-01-20","cited_by_count":5,"area":null},{"id":"2103.08889","title":"Quick Learning Mechanism with Cross-Domain Adaptation for Intelligent Fault Diagnosis","created":"2021-03-16","cited_by_count":5,"area":null}],"next_cursor":"100"}