{"list":"other","total":59,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"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":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"1611.09268","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","created":"2016-11-28","cited_by_count":1605},{"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":"1803.02155","title":"Self-Attention with Relative Position Representations","created":"2018-03-06","cited_by_count":1120},{"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":"2402.03216","title":"M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation","created":"2024-02-05","cited_by_count":1073},{"id":"2306.15595","title":"Extending Context Window of Large Language Models via Positional Interpolation","created":"2023-06-27","cited_by_count":740},{"id":"2412.13663","title":"Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference","created":"2024-12-18","cited_by_count":554},{"id":"1705.03122","title":"Convolutional Sequence to Sequence Learning","created":"2017-05-08","cited_by_count":552},{"id":"2311.16867","title":"The Falcon Series of Open Language Models","created":"2023-11-28","cited_by_count":535},{"id":"1808.03314","title":"Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network","created":"2018-08-09","cited_by_count":420},{"id":"1912.10077","title":"Are Transformers universal approximators of sequence-to-sequence functions?","created":"2019-12-20","cited_by_count":406},{"id":"2304.08467","title":"Learning to Compress Prompts with Gist Tokens","created":"2023-04-17","cited_by_count":390},{"id":"2305.19466","title":"The Impact of Positional Encoding on Length Generalization in Transformers","created":"2023-05-31","cited_by_count":327},{"id":"2103.16716","title":"BASE Layers: Simplifying Training of Large, Sparse Models","created":"2021-03-30","cited_by_count":320},{"id":"1809.10853","title":"Adaptive Input Representations for Neural Language Modeling","created":"2018-09-28","cited_by_count":226},{"id":"1806.00187","title":"Scaling Neural Machine Translation","created":"2018-06-01","cited_by_count":204},{"id":"2310.16028","title":"What Algorithms can Transformers Learn? A Study in Length Generalization","created":"2023-10-24","cited_by_count":199},{"id":"2203.16634","title":"Transformer Language Models without Positional Encodings Still Learn Positional Information","created":"2022-03-30","cited_by_count":150},{"id":"2307.03170","title":"Focused Transformer: Contrastive Training for Context Scaling","created":"2023-07-06","cited_by_count":133},{"id":"2108.12284","title":"The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers","created":"2021-08-26","cited_by_count":117},{"id":"2305.16843","title":"Randomized Positional Encodings Boost Length Generalization of Transformers","created":"2023-05-26","cited_by_count":117},{"id":"2410.06205","title":"Round and Round We Go! What makes Rotary Positional Encodings useful?","created":"2024-10-08","cited_by_count":115},{"id":"2309.10400","title":"PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training","created":"2023-09-19","cited_by_count":111},{"id":"2205.09921","title":"KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation","created":"2022-05-20","cited_by_count":86},{"id":"2007.12749","title":"Hard negative examples are hard, but useful","created":"2020-07-24","cited_by_count":82},{"id":"2311.14737","title":"Positional Description Matters for Transformers Arithmetic","created":"2023-11-22","cited_by_count":56},{"id":"2405.18719","title":"Contextual Position Encoding: Learning to Count What's Important","created":"2024-05-29","cited_by_count":54},{"id":"2405.14591","title":"Base of RoPE Bounds Context Length","created":"2024-05-23","cited_by_count":52},{"id":"2106.03143","title":"CAPE: Encoding Relative Positions with Continuous Augmented Positional Embeddings","created":"2021-06-06","cited_by_count":47},{"id":"2404.12224","title":"Length Generalization of Causal Transformers without Position Encoding","created":"2024-04-18","cited_by_count":47},{"id":"2212.10356","title":"Dissecting Transformer Length Extrapolation via the Lens of Receptive Field Analysis","created":"2022-12-20","cited_by_count":42},{"id":"2104.08698","title":"A Simple and Effective Positional Encoding for Transformers","created":"2021-04-18","cited_by_count":37},{"id":"2109.05644","title":"SHAPE: Shifted Absolute Position Embedding for Transformers","created":"2021-09-13","cited_by_count":37},{"id":"2405.14722","title":"DAPE: Data-Adaptive Positional Encoding for Length Extrapolation","created":"2024-05-23","cited_by_count":31},{"id":"2401.16421","title":"Two Stones Hit One Bird: Bilevel Positional Encoding for Better Length Extrapolation","created":"2024-01-29","cited_by_count":24},{"id":"2310.04418","title":"Functional Interpolation for Relative Positions Improves Long Context Transformers","created":"2023-10-06","cited_by_count":18},{"id":"2310.04861","title":"Uncovering hidden geometry in Transformers via disentangling position and context","created":"2023-10-07","cited_by_count":18},{"id":"2405.18009","title":"Exploring Context Window of Large Language Models via Decomposed Positional Vectors","created":"2024-05-28","cited_by_count":18},{"id":"2406.07138","title":"An Efficient Recipe for Long Context Extension via Middle-Focused Positional Encoding","created":"2024-06-11","cited_by_count":16},{"id":"2410.04798","title":"DAPE V2: Process Attention Score as Feature Map for Length Extrapolation","created":"2024-10-07","cited_by_count":10},{"id":"2501.00712","title":"Rethinking Addressing in Language Models via Contexualized Equivariant Positional Encoding","created":"2025-01-01","cited_by_count":4},{"id":"2403.17698","title":"MEP: Multiple Kernel Learning Enhancing Relative Positional Encoding Length Extrapolation","created":"2024-03-26","cited_by_count":3}],"next_cursor":null}