{"list":"other","total":52,"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":"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":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"2308.14508","title":"LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding","created":"2023-08-28","cited_by_count":1417},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"1803.02155","title":"Self-Attention with Relative Position Representations","created":"2018-03-06","cited_by_count":1120},{"id":"1912.08777","title":"PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization","created":"2019-12-18","cited_by_count":1102},{"id":"2112.00114","title":"Show Your Work: Scratchpads for Intermediate Computation with Language Models","created":"2021-11-30","cited_by_count":886},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827},{"id":"2306.15595","title":"Extending Context Window of Large Language Models via Positional Interpolation","created":"2023-06-27","cited_by_count":740},{"id":"1912.10077","title":"Are Transformers universal approximators of sequence-to-sequence functions?","created":"2019-12-20","cited_by_count":406},{"id":"2305.19466","title":"The Impact of Positional Encoding on Length Generalization in Transformers","created":"2023-05-31","cited_by_count":327},{"id":"2309.16039","title":"Effective Long-Context Scaling of Foundation Models","created":"2023-09-27","cited_by_count":303},{"id":"2307.02477","title":"Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks","created":"2023-07-05","cited_by_count":246},{"id":"2307.11088","title":"L-Eval: Instituting Standardized Evaluation for Long Context Language Models","created":"2023-07-20","cited_by_count":233},{"id":"1908.11775","title":"Transformer Dissection: A Unified Understanding of Transformer's Attention via the Lens of Kernel","created":"2019-08-30","cited_by_count":213},{"id":"2310.16028","title":"What Algorithms can Transformers Learn? A Study in Length Generalization","created":"2023-10-24","cited_by_count":199},{"id":"2006.15595","title":"Rethinking Positional Encoding in Language Pre-training","created":"2020-06-28","cited_by_count":197},{"id":"2305.14196","title":"ZeroSCROLLS: A Zero-Shot Benchmark for Long Text Understanding","created":"2023-05-23","cited_by_count":176},{"id":"2203.16634","title":"Transformer Language Models without Positional Encodings Still Learn Positional Information","created":"2022-03-30","cited_by_count":150},{"id":"2310.05209","title":"Scaling Laws of RoPE-based Extrapolation","created":"2023-10-08","cited_by_count":125},{"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":"2102.11090","title":"Position Information in Transformers: An Overview","created":"2021-02-22","cited_by_count":103},{"id":"2305.15269","title":"Testing the General Deductive Reasoning Capacity of Large Language Models Using OOD Examples","created":"2023-05-24","cited_by_count":84},{"id":"2009.13658","title":"Improve Transformer Models with Better Relative Position Embeddings","created":"2020-09-28","cited_by_count":73},{"id":"2103.14636","title":"A Practical Survey on Faster and Lighter Transformers","created":"2021-03-26","cited_by_count":73},{"id":"2301.13105","title":"Generalization on the Unseen, Logic Reasoning and Degree Curriculum","created":"2023-01-30","cited_by_count":73},{"id":"2003.09229","title":"Learning to Encode Position for Transformer with Continuous Dynamical Model","created":"2020-03-13","cited_by_count":61},{"id":"1912.12333","title":"Encoding word order in complex embeddings","created":"2019-12-27","cited_by_count":53},{"id":"2106.03143","title":"CAPE: Encoding Relative Positions with Continuous Augmented Positional Embeddings","created":"2021-06-06","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":"2109.05644","title":"SHAPE: Shifted Absolute Position Embedding for Transformers","created":"2021-09-13","cited_by_count":37},{"id":"1911.03872","title":"Location Attention for Extrapolation to Longer Sequences","created":"2019-11-10","cited_by_count":33},{"id":"2308.10882","title":"Giraffe: Adventures in Expanding Context Lengths in LLMs","created":"2023-08-21","cited_by_count":33},{"id":"2106.01950","title":"The Case for Translation-Invariant Self-Attention in Transformer-Based Language Models","created":"2021-06-03","cited_by_count":23},{"id":"2305.13571","title":"Latent Positional Information is in the Self-Attention Variance of Transformer Language Models Without Positional Embeddings","created":"2023-05-23","cited_by_count":23},{"id":"2311.00684","title":"Attention Alignment and Flexible Positional Embeddings Improve Transformer Length Extrapolation","created":"2023-11-01","cited_by_count":9},{"id":"1805.06648","title":"Extrapolation in NLP","created":"2018-05-17","cited_by_count":2}],"next_cursor":null}