{"list":"other","total":58,"rows":[{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"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":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"id":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"id":"2405.21060","title":"Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality","created":"2024-05-31","cited_by_count":1336},{"id":"2406.17557","title":"The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale","created":"2024-06-25","cited_by_count":1160},{"id":"1606.04838","title":"Optimization Methods for Large-Scale Machine Learning","created":"2016-06-15","cited_by_count":1150},{"id":"2606.19348","title":"DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence","created":"2026-04-26","cited_by_count":1040},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"2412.06464","title":"Gated Delta Networks: Improving Mamba2 with Delta Rule","created":"2024-12-09","cited_by_count":532},{"id":"2508.06471","title":"GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models","created":"2025-08-08","cited_by_count":467},{"id":"2502.16982","title":"Muon is Scalable for LLM Training","created":"2025-02-24","cited_by_count":428},{"id":"1802.09568","title":"Shampoo: Preconditioned Stochastic Tensor Optimization","created":"2018-02-26","cited_by_count":426},{"id":"2102.06701","title":"Explaining Neural Scaling Laws","created":"2021-02-12","cited_by_count":363},{"id":"2203.03466","title":"Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer","created":"2022-03-07","cited_by_count":288},{"id":"2409.11321","title":"SOAP: Improving and Stabilizing Shampoo using Adam","created":"2024-09-17","cited_by_count":192},{"id":"2406.07522","title":"Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling","created":"2024-06-11","cited_by_count":174},{"id":"2402.07871","title":"Scaling Laws for Fine-Grained Mixture of Experts","created":"2024-02-12","cited_by_count":173},{"id":"1706.05350","title":"L2 Regularization versus Batch and Weight Normalization","created":"2017-06-16","cited_by_count":124},{"id":"2505.16932","title":"The Polar Express: Optimal Matrix Sign Methods and Their Application to the Muon Algorithm","created":"2025-05-22","cited_by_count":110},{"id":"2310.17813","title":"A Spectral Condition for Feature Learning","created":"2023-10-26","cited_by_count":109},{"id":"2310.02244","title":"Tensor Programs VI: Feature Learning in Infinite-Depth Neural Networks","created":"2023-10-03","cited_by_count":97},{"id":"2504.05295","title":"Dion: Distributed Orthonormalized Updates","created":"2025-04-07","cited_by_count":68},{"id":"2509.01440","title":"Benchmarking Optimizers for Large Language Model Pretraining","created":"2025-09-01","cited_by_count":68},{"id":"2503.20762","title":"ASGO: Adaptive Structured Gradient Optimization","created":"2025-03-26","cited_by_count":57},{"id":"2305.17212","title":"Rotational Equilibrium: How Weight Decay Balances Learning Across Neural Networks","created":"2023-05-26","cited_by_count":53},{"id":"2406.09405","title":"Why Warmup the Learning Rate? Underlying Mechanisms and Improvements","created":"2024-06-13","cited_by_count":46},{"id":"2507.17702","title":"Towards Greater Leverage: Scaling Laws for Efficient Mixture-of-Experts Language Models","created":"2025-07-23","cited_by_count":45},{"id":"2409.19913","title":"Scaling Optimal LR Across Token Horizons","created":"2024-09-30","cited_by_count":40},{"id":"2510.16981","title":"MuonBP: Faster Muon via Block-Periodic Orthogonalization","created":"2025-10-19","cited_by_count":35},{"id":"2509.15816","title":"On the Convergence of Muon and Beyond","created":"2025-09-19","cited_by_count":31},{"id":"2507.01598","title":"Convergence Bound and Critical Batch Size of Muon Optimizer","created":"2025-07-02","cited_by_count":28},{"id":"2506.02285","title":"Why Gradients Rapidly Increase Near the End of Training","created":"2025-06-02","cited_by_count":22},{"id":"2604.09967","title":"Muon$^2$: Boosting Muon via Adaptive Second-Moment Preconditioning","created":"2026-04-11","cited_by_count":17},{"id":"2606.16899","title":"Fantastic Pretraining Optimizers and Where to Find Them II: Hyperball Optimization","created":"2026-06-15","cited_by_count":16},{"id":"2510.12402","title":"Cautious Weight Decay","created":"2025-10-14","cited_by_count":13},{"id":"2512.16928","title":"Dion2: A Simple Method to Shrink Matrix in Muon","created":"2025-12-01","cited_by_count":13},{"id":"2603.28743","title":"Rethinking Language Model Scaling under Transferable Hypersphere Optimization","created":"2026-03-30","cited_by_count":12},{"id":"2506.04645","title":"Inference economics of language models","created":"2025-06-05","cited_by_count":9},{"id":"2405.14005","title":"Neural Scaling Laws in Robotics","created":"2024-05-22","cited_by_count":7},{"id":"2605.10797","title":"Muown: Row-Norm Control for Muon Optimization","created":"2026-05-11","cited_by_count":6},{"id":"2602.16687","title":"Scaling Open Discrete Audio Foundation Models with Interleaved Semantic, Acoustic, and Text Tokens","created":"2026-02-18","cited_by_count":4},{"id":"2606.27715","title":"Aurora: A Leverage-Aware Spectral Optimizer","created":"2026-06-26","cited_by_count":4},{"id":"2605.23061","title":"Anytime Training with Schedule-Free Spectral Optimization","created":"2026-05-21","cited_by_count":3},{"id":"2605.29157","title":"Parallax: Parameterized Local Linear Attention for Language Modeling","created":"2026-05-27","cited_by_count":1}],"next_cursor":null}