{"list":"other","total":57,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"2206.14486","title":"Beyond neural scaling laws: beating power law scaling via data pruning","created":"2022-06-29","cited_by_count":528},{"id":"1511.05641","title":"Net2Net: Accelerating Learning via Knowledge Transfer","created":"2015-11-18","cited_by_count":250},{"id":"2502.07529","title":"Training Deep Learning Models with Norm-Constrained LMOs","created":"2025-02-11","cited_by_count":192},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186},{"id":"2303.01486","title":"Understanding plasticity in neural networks","created":"2023-03-02","cited_by_count":174},{"id":"2405.18392","title":"Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations","created":"2024-05-28","cited_by_count":170},{"id":"2210.14891","title":"Broken Neural Scaling Laws","created":"2022-10-26","cited_by_count":109},{"id":"2305.13035","title":"Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design","created":"2023-05-22","cited_by_count":89},{"id":"2406.19146","title":"Resolving Discrepancies in Compute-Optimal Scaling of Language Models","created":"2024-06-27","cited_by_count":88},{"id":"2303.00980","title":"Learning to Grow Pretrained Models for Efficient Transformer Training","created":"2023-03-02","cited_by_count":83},{"id":"2505.02222","title":"Practical Efficiency of Muon for Pretraining","created":"2025-05-04","cited_by_count":80},{"id":"2505.01618","title":"Don't be lazy: CompleteP enables compute-efficient deep transformers","created":"2025-05-02","cited_by_count":78},{"id":"2407.05872","title":"Scaling Exponents Across Parameterizations and Optimizers","created":"2024-07-08","cited_by_count":76},{"id":"2110.07143","title":"bert2BERT: Towards Reusable Pretrained Language Models","created":"2021-10-14","cited_by_count":70},{"id":"2201.05125","title":"GradMax: Growing Neural Networks using Gradient Information","created":"2022-01-13","cited_by_count":66},{"id":"1603.01670","title":"Network Morphism","created":"2016-03-05","cited_by_count":65},{"id":"2203.06211","title":"Staged Training for Transformer Language Models","created":"2022-03-11","cited_by_count":49},{"id":"2306.13812","title":"Maintaining Plasticity in Deep Continual Learning","created":"2023-06-23","cited_by_count":43},{"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},{"id":"2305.18411","title":"Feature-Learning Networks Are Consistent Across Widths At Realistic Scales","created":"2023-05-28","cited_by_count":41},{"id":"2409.19913","title":"Scaling Optimal LR Across Token Horizons","created":"2024-09-30","cited_by_count":40},{"id":"2105.13880","title":"Knowledge Inheritance for Pre-trained Language Models","created":"2021-05-28","cited_by_count":38},{"id":"2305.02869","title":"Masked Structural Growth for 2x Faster Language Model Pre-training","created":"2023-05-04","cited_by_count":33},{"id":"2407.01704","title":"Weight Clipping for Deep Continual and Reinforcement Learning","created":"2024-07-01","cited_by_count":29},{"id":"2407.17465","title":"u-$\\mu$P: The Unit-Scaled Maximal Update Parametrization","created":"2024-07-24","cited_by_count":29},{"id":"2409.12903","title":"Scaling Smart: Accelerating Large Language Model Pre-training with Small Model Initialization","created":"2024-09-19","cited_by_count":29},{"id":"2310.07999","title":"LEMON: Lossless model expansion","created":"2023-10-12","cited_by_count":23},{"id":"2410.23922","title":"Analyzing & Reducing the Need for Learning Rate Warmup in GPT Training","created":"2024-10-31","cited_by_count":22},{"id":"2507.02119","title":"Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks","created":"2025-07-02","cited_by_count":22},{"id":"2405.15743","title":"Sparse maximal update parameterization: A holistic approach to sparse training dynamics","created":"2024-05-24","cited_by_count":16},{"id":"2306.08055","title":"Tune As You Scale: Hyperparameter Optimization For Compute Efficient Training","created":"2023-06-13","cited_by_count":9},{"id":"2509.25087","title":"Scaling with Collapse: Efficient and Predictable Training of LLM Families","created":"2025-09-29","cited_by_count":9},{"id":"2510.03871","title":"Optimal Scaling Needs Optimal Norm","created":"2025-10-04","cited_by_count":8},{"id":"2406.00153","title":"$\\mu$LO: Compute-Efficient Meta-Generalization of Learned Optimizers","created":"2024-05-31","cited_by_count":7},{"id":"2207.07267","title":"ScaleNet: Searching for the Model to Scale","created":"2022-07-15","cited_by_count":4},{"id":"2311.03233","title":"Navigating Scaling Laws: Compute Optimality in Adaptive Model Training","created":"2023-11-06","cited_by_count":4},{"id":"2406.02469","title":"Landscape-Aware Growing: The Power of a Little LAG","created":"2024-06-04","cited_by_count":4},{"id":"2602.02472","title":"SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning","created":"2026-02-02","cited_by_count":4},{"id":"2308.11331","title":"GrowCLIP: Data-aware Automatic Model Growing for Large-scale Contrastive Language-Image Pre-training","created":"2023-08-22","cited_by_count":3},{"id":"2604.04281","title":"Preservation Is Not Enough for Width Growth: Regime-Sensitive Selection of Dense LM Warm Starts","created":"2026-04-05","cited_by_count":1}],"next_cursor":null}