{"list":"other","total":51,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"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":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1702.08734","title":"Billion-scale similarity search with GPUs","created":"2017-02-28","cited_by_count":2497},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"2204.07705","title":"Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks","created":"2022-04-16","cited_by_count":868},{"id":"2106.05974","title":"Scaling Vision with Sparse Mixture of Experts","created":"2021-06-10","cited_by_count":747},{"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":"2201.05596","title":"DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale","created":"2022-01-14","cited_by_count":404},{"id":"2212.09689","title":"Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor","created":"2022-12-19","cited_by_count":397},{"id":"2103.16716","title":"BASE Layers: Simplifying Training of Large, Sparse Models","created":"2021-03-30","cited_by_count":320},{"id":"2310.17157","title":"Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time","created":"2023-10-26","cited_by_count":252},{"id":"2106.04426","title":"Hash Layers For Large Sparse Models","created":"2021-06-08","cited_by_count":237},{"id":"2211.15841","title":"MegaBlocks: Efficient Sparse Training with Mixture-of-Experts","created":"2022-11-29","cited_by_count":209},{"id":"2206.03382","title":"Tutel: Adaptive Mixture-of-Experts at Scale","created":"2022-06-07","cited_by_count":201},{"id":"2002.08307","title":"Compressing BERT: Studying the Effects of Weight Pruning on Transfer Learning","created":"2020-02-19","cited_by_count":185},{"id":"2312.11514","title":"LLM in a flash: Efficient Large Language Model Inference with Limited Memory","created":"2023-12-12","cited_by_count":177},{"id":"2112.10684","title":"Efficient Large Scale Language Modeling with Mixtures of Experts","created":"2021-12-20","cited_by_count":175},{"id":"2204.09179","title":"On the Representation Collapse of Sparse Mixture of Experts","created":"2022-04-20","cited_by_count":157},{"id":"2110.01786","title":"MoEfication: Transformer Feed-forward Layers are Mixtures of Experts","created":"2021-10-05","cited_by_count":152},{"id":"2108.05036","title":"DEMix Layers: Disentangling Domains for Modular Language Modeling","created":"2021-08-11","cited_by_count":132},{"id":"2210.06313","title":"The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers","created":"2022-10-12","cited_by_count":122},{"id":"2110.04260","title":"Taming Sparsely Activated Transformer with Stochastic Experts","created":"2021-10-08","cited_by_count":113},{"id":"2310.04564","title":"ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models","created":"2023-10-06","cited_by_count":94},{"id":"2010.13369","title":"Accelerating Training of Transformer-Based Language Models with Progressive Layer Dropping","created":"2020-10-26","cited_by_count":93},{"id":"2306.03745","title":"Soft Merging of Experts with Adaptive Routing","created":"2023-06-06","cited_by_count":90},{"id":"2104.07705","title":"How to Train BERT with an Academic Budget","created":"2021-04-15","cited_by_count":80},{"id":"2302.03202","title":"Exploring the Benefits of Training Expert Language Models over Instruction Tuning","created":"2023-02-07","cited_by_count":80},{"id":"2402.03804","title":"ReLU$^2$ Wins: Discovering Efficient Activation Functions for Sparse LLMs","created":"2024-02-06","cited_by_count":67},{"id":"2211.07349","title":"Finding Skill Neurons in Pre-trained Transformer-based Language Models","created":"2022-11-14","cited_by_count":66},{"id":"2305.12281","title":"Lifelong Language Pretraining with Distribution-Specialized Experts","created":"2023-05-20","cited_by_count":66},{"id":"2210.05144","title":"Mixture of Attention Heads: Selecting Attention Heads Per Token","created":"2022-10-11","cited_by_count":60},{"id":"2303.01610","title":"Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers","created":"2023-03-02","cited_by_count":59},{"id":"2404.05567","title":"Dense Training, Sparse Inference: Rethinking Training of Mixture-of-Experts Language Models","created":"2024-04-08","cited_by_count":42},{"id":"2105.13880","title":"Knowledge Inheritance for Pre-trained Language Models","created":"2021-05-28","cited_by_count":38},{"id":"2204.07675","title":"MoEBERT: from BERT to Mixture-of-Experts via Importance-Guided Adaptation","created":"2022-04-15","cited_by_count":37},{"id":"2305.18390","title":"Emergent Modularity in Pre-trained Transformers","created":"2023-05-28","cited_by_count":37},{"id":"2205.14336","title":"Gating Dropout: Communication-efficient Regularization for Sparsely Activated Transformers","created":"2022-05-28","cited_by_count":22},{"id":"2403.08245","title":"Scattered Mixture-of-Experts Implementation","created":"2024-03-13","cited_by_count":15},{"id":"2205.12399","title":"Sparse Mixers: Combining MoE and Mixing to build a more efficient BERT","created":"2022-05-24","cited_by_count":12},{"id":"2208.01313","title":"Unified Normalization for Accelerating and Stabilizing Transformers","created":"2022-08-02","cited_by_count":6}],"next_cursor":null}