{"list":"other","total":68,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"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":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"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":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004},{"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":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"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":"2305.13245","title":"GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints","created":"2023-05-22","cited_by_count":1346},{"id":"2306.00978","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","created":"2023-06-01","cited_by_count":1298},{"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":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"id":"2304.12244","title":"WizardLM: Empowering large pre-trained language models to follow complex instructions","created":"2023-04-24","cited_by_count":1125},{"id":"2606.19348","title":"DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence","created":"2026-04-26","cited_by_count":1040},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"2401.06066","title":"DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models","created":"2024-01-11","cited_by_count":867},{"id":"2404.06395","title":"MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies","created":"2024-04-09","cited_by_count":723},{"id":"2304.11277","title":"PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel","created":"2023-04-21","cited_by_count":660},{"id":"2309.00071","title":"YaRN: Efficient Context Window Extension of Large Language Models","created":"2023-08-31","cited_by_count":601},{"id":"2601.11868","title":"Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces","created":"2026-01-17","cited_by_count":585},{"id":"2306.11644","title":"Textbooks Are All You Need","created":"2023-06-20","cited_by_count":569},{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546},{"id":"2402.00159","title":"Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research","created":"2024-01-31","cited_by_count":483},{"id":"2405.16406","title":"SpinQuant: LLM quantization with learned rotations","created":"2024-05-26","cited_by_count":471},{"id":"2502.16982","title":"Muon is Scalable for LLM Training","created":"2025-02-24","cited_by_count":428},{"id":"2202.08906","title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","created":"2022-02-17","cited_by_count":399},{"id":"2305.10429","title":"DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining","created":"2023-05-17","cited_by_count":399},{"id":"2406.11794","title":"DataComp-LM: In search of the next generation of training sets for language models","created":"2024-06-17","cited_by_count":398},{"id":"2205.05198","title":"Reducing Activation Recomputation in Large Transformer Models","created":"2022-05-10","cited_by_count":302},{"id":"2401.03065","title":"CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution","created":"2024-01-05","cited_by_count":300},{"id":"2505.06708","title":"Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free","created":"2025-05-10","cited_by_count":283},{"id":"2509.16941","title":"SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?","created":"2025-09-21","cited_by_count":279},{"id":"2506.13585","title":"MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention","created":"2025-06-16","cited_by_count":263},{"id":"2306.15895","title":"Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias","created":"2023-06-28","cited_by_count":232},{"id":"2403.16952","title":"Data Mixing Laws: Optimizing Data Mixtures by Predicting Language Modeling Performance","created":"2024-03-25","cited_by_count":184},{"id":"2407.01492","title":"RegMix: Data Mixture as Regression for Language Model Pre-training","created":"2024-07-01","cited_by_count":177},{"id":"2401.16380","title":"Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling","created":"2024-01-29","cited_by_count":161},{"id":"2412.02595","title":"Nemotron-CC: Transforming Common Crawl into a Refined Long-Horizon Pretraining Dataset","created":"2024-12-03","cited_by_count":160},{"id":"2505.07608","title":"MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining","created":"2025-05-12","cited_by_count":121},{"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":"2205.10287","title":"On the SDEs and Scaling Rules for Adaptive Gradient Algorithms","created":"2022-05-20","cited_by_count":104},{"id":"2512.20848","title":"Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2025-12-23","cited_by_count":104},{"id":"2410.06511","title":"TorchTitan: One-stop PyTorch native solution for production ready LLM pre-training","created":"2024-10-09","cited_by_count":85},{"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":"2310.16248","title":"GlotLID: Language Identification for Low-Resource Languages","created":"2023-10-24","cited_by_count":39},{"id":"2109.07460","title":"Efficient Domain Adaptation of Language Models via Adaptive Tokenization","created":"2021-09-15","cited_by_count":34},{"id":"2601.20088","title":"Quantization-Aware Distillation for NVFP4 Inference Accuracy Recovery","created":"2026-01-27","cited_by_count":22},{"id":"2602.12237","title":"Olmix: A Framework for Data Mixing Throughout LM Development","created":"2026-02-12","cited_by_count":13},{"id":"2511.13940","title":"ParallelKittens: Systematic and Practical Simplification of Multi-GPU AI Kernels","created":"2025-11-17","cited_by_count":12},{"id":"2510.24397","title":"APTBench: Benchmarking Agentic Potential of Base LLMs During Pre-Training","created":"2025-10-28","cited_by_count":11},{"id":"2505.20133","title":"Token Distillation: Attention-aware Input Embeddings For New Tokens","created":"2025-05-26","cited_by_count":6},{"id":"2602.12414","title":"propella-1: Multi-Property Document Annotation for LLM Data Curation at Scale","created":"2026-02-12","cited_by_count":6},{"id":"2605.12715","title":"Scaling Laws for Mixture Pretraining Under Data Constraints","created":"2026-05-12","cited_by_count":6},{"id":"2502.15950","title":"Optimizing Pre-Training Data Mixtures with Mixtures of Data Expert Models","created":"2025-02-21","cited_by_count":5}],"next_cursor":null}