{"list":"other","total":59,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"2305.01210","title":"Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation","created":"2023-05-02","cited_by_count":1391},{"id":"2508.10925","title":"gpt-oss-120b & gpt-oss-20b Model Card","created":"2025-08-08","cited_by_count":1386},{"id":"2404.06654","title":"RULER: What's the Real Context Size of Your Long-Context Language Models?","created":"2024-04-09","cited_by_count":1346},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"2512.02556","title":"DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models","created":"2025-12-02","cited_by_count":815},{"id":"1911.02150","title":"Fast Transformer Decoding: One Write-Head is All You Need","created":"2019-11-06","cited_by_count":717},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694},{"id":"2507.20534","title":"Kimi K2: Open Agentic Intelligence","created":"2025-07-28","cited_by_count":567},{"id":"2412.06464","title":"Gated Delta Networks: Improving Mamba2 with Delta Rule","created":"2024-12-09","cited_by_count":532},{"id":"2210.03057","title":"Language Models are Multilingual Chain-of-Thought Reasoners","created":"2022-10-06","cited_by_count":530},{"id":"2102.11174","title":"Linear Transformers Are Secretly Fast Weight Programmers","created":"2021-02-22","cited_by_count":502},{"id":"2502.16982","title":"Muon is Scalable for LLM Training","created":"2025-02-24","cited_by_count":428},{"id":"2407.01489","title":"Agentless: Demystifying LLM-based Software Engineering Agents","created":"2024-07-01","cited_by_count":421},{"id":"2403.03853","title":"ShortGPT: Layers in Large Language Models are More Redundant Than You Expect","created":"2024-03-06","cited_by_count":383},{"id":"1812.06162","title":"An Empirical Model of Large-Batch Training","created":"2018-12-14","cited_by_count":281},{"id":"1505.00387","title":"Highway Networks","created":"2015-05-03","cited_by_count":260},{"id":"2607.02770","title":"Gemma 4 Technical Report","created":"2026-07-02","cited_by_count":259},{"id":"2501.01005","title":"FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving","created":"2025-01-02","cited_by_count":258},{"id":"2309.14322","title":"Small-scale proxies for large-scale Transformer training instabilities","created":"2023-09-25","cited_by_count":183},{"id":"2405.05254","title":"You Only Cache Once: Decoder-Decoder Architectures for Language Models","created":"2024-05-08","cited_by_count":144},{"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":"2512.24880","title":"mHC: Manifold-Constrained Hyper-Connections","created":"2025-12-31","cited_by_count":88},{"id":"2411.19799","title":"INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge","created":"2024-11-29","cited_by_count":86},{"id":"2409.19606","title":"Hyper-Connections","created":"2024-09-29","cited_by_count":84},{"id":"2505.02222","title":"Practical Efficiency of Muon for Pretraining","created":"2025-05-04","cited_by_count":80},{"id":"2410.21676","title":"How Does Critical Batch Size Scale in Pre-training?","created":"2024-10-29","cited_by_count":73},{"id":"2501.11873","title":"Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models","created":"2025-01-21","cited_by_count":54},{"id":"2501.16975","title":"Over-Tokenized Transformer: Vocabulary is Generally Worth Scaling","created":"2025-01-28","cited_by_count":44},{"id":"2603.12201","title":"IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse","created":"2026-03-12","cited_by_count":31},{"id":"2410.17897","title":"Value Residual Learning","created":"2024-10-23","cited_by_count":27},{"id":"2601.22966","title":"A Unified View of Attention and Residual Sinks: Outlier-Driven Rescaling is Essential for Transformer Training","created":"2026-01-30","cited_by_count":23},{"id":"2502.01637","title":"Scaling Embedding Layers in Language Models","created":"2025-02-03","cited_by_count":20},{"id":"2207.06366","title":"N-Grammer: Augmenting Transformers with latent n-grams","created":"2022-07-13","cited_by_count":14},{"id":"2301.13310","title":"Alternating Updates for Efficient Transformers","created":"2023-01-30","cited_by_count":13},{"id":"2601.10639","title":"STEM: Scaling Transformers with Embedding Modules","created":"2026-01-15","cited_by_count":12},{"id":"2104.04552","title":"Lookup-Table Recurrent Language Models for Long Tail Speech Recognition","created":"2021-04-09","cited_by_count":9},{"id":"2509.24745","title":"ProxyAttn: Guided Sparse Attention via Representative Heads","created":"2025-09-29","cited_by_count":9},{"id":"2602.06079","title":"Canzona: A Unified, Asynchronous, and Load-Balanced Framework for Distributed Matrix-based Optimizers","created":"2026-02-04","cited_by_count":4},{"id":"2604.21724","title":"Beyond N-gram: Data-Aware X-GRAM Extraction for Efficient Embedding Parameter Scaling","created":"2026-04-23","cited_by_count":1}],"next_cursor":null}