{"list":"other","total":100,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"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":"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":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"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":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"2309.17453","title":"Efficient Streaming Language Models with Attention Sinks","created":"2023-09-29","cited_by_count":2186},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1808.06226","title":"SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing","created":"2018-08-19","cited_by_count":1989},{"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":"1905.00414","title":"Similarity of Neural Network Representations Revisited","created":"2019-05-01","cited_by_count":1755},{"id":"1607.04606","title":"Enriching Word Vectors with Subword Information","created":"2016-07-15","cited_by_count":1583},{"id":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"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":"2012.14913","title":"Transformer Feed-Forward Layers Are Key-Value Memories","created":"2020-12-29","cited_by_count":1336},{"id":"2112.04426","title":"Improving language models by retrieving from trillions of tokens","created":"2021-12-08","cited_by_count":1293},{"id":"2212.10511","title":"When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories","created":"2022-12-20","cited_by_count":1128},{"id":"2108.12409","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","created":"2021-08-27","cited_by_count":1103},{"id":"1905.05950","title":"BERT Rediscovers the Classical NLP Pipeline","created":"2019-05-15","cited_by_count":1059},{"id":"2210.07229","title":"Mass-Editing Memory in a Transformer","created":"2022-10-13","cited_by_count":1001},{"id":"1702.03118","title":"Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning","created":"2017-02-10","cited_by_count":950},{"id":"1903.00161","title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","created":"2019-03-01","cited_by_count":903},{"id":"1704.04683","title":"RACE: Large-scale ReAding Comprehension Dataset From Examinations","created":"2017-04-15","cited_by_count":861},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827},{"id":"2305.06161","title":"StarCoder: may the source be with you!","created":"2023-05-09","cited_by_count":799},{"id":"2304.06364","title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","created":"2023-04-13","cited_by_count":716},{"id":"2305.08322","title":"C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models","created":"2023-05-15","cited_by_count":708},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694},{"id":"2401.02954","title":"DeepSeek LLM: Scaling Open-Source Language Models with Longtermism","created":"2024-01-05","cited_by_count":642},{"id":"2303.08112","title":"Eliciting Latent Predictions from Transformers with the Tuned Lens","created":"2023-03-14","cited_by_count":623},{"id":"2104.08696","title":"Knowledge Neurons in Pretrained Transformers","created":"2021-04-18","cited_by_count":601},{"id":"2309.00071","title":"YaRN: Efficient Context Window Extension of Large Language Models","created":"2023-08-31","cited_by_count":601},{"id":"2210.03057","title":"Language Models are Multilingual Chain-of-Thought Reasoners","created":"2022-10-06","cited_by_count":530},{"id":"2306.09212","title":"CMMLU: Measuring massive multitask language understanding in Chinese","created":"2023-06-15","cited_by_count":449},{"id":"2210.13382","title":"Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task","created":"2022-10-24","cited_by_count":431},{"id":"2502.16982","title":"Muon is Scalable for LLM Training","created":"2025-02-24","cited_by_count":428},{"id":"2103.16716","title":"BASE Layers: Simplifying Training of Large, Sparse Models","created":"2021-03-30","cited_by_count":320},{"id":"2401.03065","title":"CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution","created":"2024-01-05","cited_by_count":300},{"id":"2401.06102","title":"Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models","created":"2024-01-11","cited_by_count":235},{"id":"1605.07648","title":"FractalNet: Ultra-Deep Neural Networks without Residuals","created":"2016-05-24","cited_by_count":216},{"id":"2408.15664","title":"Auxiliary-Loss-Free Load Balancing Strategy for Mixture-of-Experts","created":"2024-08-28","cited_by_count":205},{"id":"2305.05065","title":"Recommender Systems with Generative Retrieval","created":"2023-05-08","cited_by_count":198},{"id":"2510.26692","title":"Kimi Linear: An Expressive, Efficient Attention Architecture","created":"2025-10-30","cited_by_count":196},{"id":"2406.04127","title":"Are We Done with MMLU?","created":"2024-06-06","cited_by_count":194},{"id":"2401.17377","title":"Infini-gram: Scaling Unbounded n-gram Language Models to a Trillion Tokens","created":"2024-01-30","cited_by_count":153},{"id":"2105.07464","title":"Few-NERD: A Few-Shot Named Entity Recognition Dataset","created":"2021-05-16","cited_by_count":152},{"id":"2410.02660","title":"How to Train Long-Context Language Models (Effectively)","created":"2024-10-03","cited_by_count":146},{"id":"2412.09871","title":"Byte Latent Transformer: Patches Scale Better Than Tokens","created":"2024-12-13","cited_by_count":146},{"id":"1907.05242","title":"Large Memory Layers with Product Keys","created":"2019-07-10","cited_by_count":124},{"id":"2305.02437","title":"Lift Yourself Up: Retrieval-augmented Text Generation with Self Memory","created":"2023-05-03","cited_by_count":103},{"id":"2210.16156","title":"Reliability of CKA as a Similarity Measure in Deep Learning","created":"2022-10-28","cited_by_count":87},{"id":"2409.19606","title":"Hyper-Connections","created":"2024-09-29","cited_by_count":84},{"id":"1904.09679","title":"Investigating Prior Knowledge for Challenging Chinese Machine Reading Comprehension","created":"2019-04-21","cited_by_count":81},{"id":"2407.04153","title":"Mixture of A Million Experts","created":"2024-07-04","cited_by_count":72},{"id":"2410.23771","title":"What is Wrong with Perplexity for Long-context Language Modeling?","created":"2024-10-31","cited_by_count":69},{"id":"1909.02107","title":"Compositional Embeddings Using Complementary Partitions for Memory-Efficient Recommendation Systems","created":"2019-09-04","cited_by_count":68},{"id":"2304.06762","title":"Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study","created":"2023-04-13","cited_by_count":63},{"id":"2503.13423","title":"SuperBPE: Space Travel for Language Models","created":"2025-03-17","cited_by_count":63},{"id":"2101.11714","title":"TT-Rec: Tensor Train Compression for Deep Learning Recommendation Models","created":"2021-01-25","cited_by_count":58},{"id":"1709.03933","title":"Hash Embeddings for Efficient Word Representations","created":"2017-09-12","cited_by_count":55},{"id":"2306.08121","title":"Better Generalization with Semantic IDs: A Case Study in Ranking for Recommendations","created":"2023-06-13","cited_by_count":52},{"id":"2505.13898","title":"Do Language Models Use Their Depth Efficiently?","created":"2025-05-20","cited_by_count":50},{"id":"2412.09764","title":"Memory Layers at Scale","created":"2024-12-12","cited_by_count":48},{"id":"2501.16975","title":"Over-Tokenized Transformer: Vocabulary is Generally Worth Scaling","created":"2025-01-28","cited_by_count":44},{"id":"2101.07577","title":"Learnable Embedding Sizes for Recommender Systems","created":"2021-01-19","cited_by_count":42},{"id":"1909.11810","title":"Mixed Dimension Embeddings with Application to Memory-Efficient Recommendation Systems","created":"2019-09-25","cited_by_count":41},{"id":"1907.04471","title":"Neural Input Search for Large Scale Recommendation Models","created":"2019-07-10","cited_by_count":39},{"id":"2010.10784","title":"Learning to Embed Categorical Features without Embedding Tables for Recommendation","created":"2020-10-21","cited_by_count":38},{"id":"2505.16381","title":"PaTH Attention: Position Encoding via Accumulating Householder Transformations","created":"2025-05-22","cited_by_count":34},{"id":"2007.14523","title":"Model Size Reduction Using Frequency Based Double Hashing for Recommender Systems","created":"2020-07-28","cited_by_count":33},{"id":"2512.17351","title":"Physics of Language Models: Part 4.1, Architecture Design and the Magic of Canon Layers","created":"2025-12-19","cited_by_count":33},{"id":"2307.06962","title":"Copy Is All You Need","created":"2023-07-13","cited_by_count":27},{"id":"2407.12034","title":"Understanding Transformers via N-gram Statistics","created":"2024-06-30","cited_by_count":26},{"id":"2002.08530","title":"Learning Multi-granular Quantized Embeddings for Large-Vocab Categorical Features in Recommender Systems","created":"2020-02-20","cited_by_count":24},{"id":"2502.01637","title":"Scaling Embedding Layers in Language Models","created":"2025-02-03","cited_by_count":20},{"id":"2411.12364","title":"Ultra-Sparse Memory Network","created":"2024-11-19","cited_by_count":19},{"id":"2106.01979","title":"CCPM: A Chinese Classical Poetry Matching Dataset","created":"2021-06-03","cited_by_count":15},{"id":"2207.06366","title":"N-Grammer: Augmenting Transformers with latent n-grams","created":"2022-07-13","cited_by_count":14},{"id":"2305.12102","title":"Unified Embedding: Battle-Tested Feature Representations for Web-Scale ML Systems","created":"2023-05-20","cited_by_count":14},{"id":"2402.17532","title":"Retrieval is Accurate Generation","created":"2024-02-27","cited_by_count":10},{"id":"2312.03256","title":"CAFE: Towards Compact, Adaptive, and Fast Embedding for Large-scale Recommendation Models","created":"2023-12-06","cited_by_count":7},{"id":"2108.02191","title":"Random Offset Block Embedding Array (ROBE) for CriteoTB Benchmark MLPerf DLRM Model : 1000$\\times$ Compression and 3.1$\\times$ Faster Inference","created":"2021-08-04","cited_by_count":4},{"id":"2301.00066","title":"Memory Augmented Lookup Dictionary based Language Modeling for Automatic Speech Recognition","created":"2022-12-30","cited_by_count":1}],"next_cursor":null}