{"list":"other","total":108,"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"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":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"2309.17453","title":"Efficient Streaming Language Models with Attention Sinks","created":"2023-09-29","cited_by_count":2186},{"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":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"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":"1912.08777","title":"PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization","created":"2019-12-18","cited_by_count":1102},{"id":"2303.17564","title":"BloombergGPT: A Large Language Model for Finance","created":"2023-03-30","cited_by_count":939},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827},{"id":"2211.09085","title":"Galactica: A Large Language Model for Science","created":"2022-11-16","cited_by_count":744},{"id":"2306.15595","title":"Extending Context Window of Large Language Models via Positional Interpolation","created":"2023-06-27","cited_by_count":740},{"id":"2309.00071","title":"YaRN: Efficient Context Window Extension of Large Language Models","created":"2023-08-31","cited_by_count":601},{"id":"2212.14052","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","created":"2022-12-28","cited_by_count":499},{"id":"2403.19887","title":"Jamba: A Hybrid Transformer-Mamba Language Model","created":"2024-03-28","cited_by_count":401},{"id":"2305.19466","title":"The Impact of Positional Encoding on Length Generalization in Transformers","created":"2023-05-31","cited_by_count":327},{"id":"2405.04517","title":"xLSTM: Extended Long Short-Term Memory","created":"2024-05-07","cited_by_count":327},{"id":"2402.13753","title":"LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens","created":"2024-02-21","cited_by_count":313},{"id":"2309.16039","title":"Effective Long-Context Scaling of Foundation Models","created":"2023-09-27","cited_by_count":303},{"id":"2002.11296","title":"Sparse Sinkhorn Attention","created":"2020-02-26","cited_by_count":251},{"id":"2402.19427","title":"Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models","created":"2024-02-29","cited_by_count":242},{"id":"2112.07916","title":"LongT5: Efficient Text-To-Text Transformer for Long Sequences","created":"2021-12-15","cited_by_count":232},{"id":"2207.02098","title":"Neural Networks and the Chomsky Hierarchy","created":"2022-07-05","cited_by_count":217},{"id":"2312.04927","title":"Zoology: Measuring and Improving Recall in Efficient Language Models","created":"2023-12-08","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":"2006.15595","title":"Rethinking Positional Encoding in Language Pre-training","created":"2020-06-28","cited_by_count":197},{"id":"2402.10171","title":"Data Engineering for Scaling Language Models to 128K Context","created":"2024-02-15","cited_by_count":186},{"id":"2306.00802","title":"Birth of a Transformer: A Memory Viewpoint","created":"2023-06-01","cited_by_count":161},{"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":"2203.16634","title":"Transformer Language Models without Positional Encodings Still Learn Positional Information","created":"2022-03-30","cited_by_count":150},{"id":"2304.09797","title":"Progressive-Hint Prompting Improves Reasoning in Large Language Models","created":"2023-04-19","cited_by_count":147},{"id":"2003.07064","title":"On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Location","created":"2020-03-16","cited_by_count":142},{"id":"2401.01325","title":"LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning","created":"2024-01-02","cited_by_count":136},{"id":"2307.03170","title":"Focused Transformer: Contrastive Training for Context Scaling","created":"2023-07-06","cited_by_count":133},{"id":"2212.10554","title":"A Length-Extrapolatable Transformer","created":"2022-12-20","cited_by_count":127},{"id":"2403.09054","title":"Keyformer: KV Cache Reduction through Key Tokens Selection for Efficient Generative Inference","created":"2024-03-14","cited_by_count":126},{"id":"2310.05209","title":"Scaling Laws of RoPE-based Extrapolation","created":"2023-10-08","cited_by_count":125},{"id":"2305.16843","title":"Randomized Positional Encodings Boost Length Generalization of Transformers","created":"2023-05-26","cited_by_count":117},{"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":"2010.03957","title":"Transformers for Modeling Physical Systems","created":"2020-10-04","cited_by_count":106},{"id":"2205.09921","title":"KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation","created":"2022-05-20","cited_by_count":86},{"id":"2402.09371","title":"Transformers Can Achieve Length Generalization But Not Robustly","created":"2024-02-14","cited_by_count":86},{"id":"2303.09752","title":"CoLT5: Faster Long-Range Transformers with Conditional Computation","created":"2023-03-17","cited_by_count":84},{"id":"2402.16617","title":"Long-Context Language Modeling with Parallel Context Encoding","created":"2024-02-26","cited_by_count":84},{"id":"2310.10638","title":"In-context Pretraining: Language Modeling Beyond Document Boundaries","created":"2023-10-16","cited_by_count":79},{"id":"2401.02669","title":"Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache","created":"2024-01-05","cited_by_count":73},{"id":"2403.04797","title":"Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding","created":"2024-03-05","cited_by_count":72},{"id":"2312.11562","title":"A Survey of Reasoning with Foundation Models","created":"2023-12-17","cited_by_count":70},{"id":"2003.02436","title":"Talking-Heads Attention","created":"2020-03-05","cited_by_count":62},{"id":"2402.17463","title":"Training-Free Long-Context Scaling of Large Language Models","created":"2024-02-27","cited_by_count":62},{"id":"2003.09229","title":"Learning to Encode Position for Transformer with Continuous Dynamical Model","created":"2020-03-13","cited_by_count":61},{"id":"2401.04658","title":"Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models","created":"2024-01-09","cited_by_count":57},{"id":"2205.13401","title":"Your Transformer May Not be as Powerful as You Expect","created":"2022-05-26","cited_by_count":55},{"id":"2403.18120","title":"Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization","created":"2024-03-26","cited_by_count":55},{"id":"2405.18719","title":"Contextual Position Encoding: Learning to Count What's Important","created":"2024-05-29","cited_by_count":54},{"id":"2407.14482","title":"ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities","created":"2024-07-19","cited_by_count":53},{"id":"2106.12566","title":"Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding","created":"2021-06-23","cited_by_count":51},{"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":"2302.02615","title":"Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling is All You Need","created":"2023-02-06","cited_by_count":46},{"id":"2310.16450","title":"CLEX: Continuous Length Extrapolation for Large Language Models","created":"2023-10-25","cited_by_count":44},{"id":"2212.10356","title":"Dissecting Transformer Length Extrapolation via the Lens of Receptive Field Analysis","created":"2022-12-20","cited_by_count":42},{"id":"2406.15486","title":"SampleAttention: Near-Lossless Acceleration of Long Context LLM Inference with Adaptive Structured Sparse Attention","created":"2024-06-17","cited_by_count":39},{"id":"2109.05644","title":"SHAPE: Shifted Absolute Position Embedding for Transformers","created":"2021-09-13","cited_by_count":37},{"id":"2401.11504","title":"With Greater Text Comes Greater Necessity: Inference-Time Training Helps Long Text Generation","created":"2024-01-21","cited_by_count":37},{"id":"2404.10830","title":"Fewer Truncations Improve Language Modeling","created":"2024-04-16","cited_by_count":35},{"id":"2405.14722","title":"DAPE: Data-Adaptive Positional Encoding for Length Extrapolation","created":"2024-05-23","cited_by_count":31},{"id":"2403.00071","title":"Resonance RoPE: Improving Context Length Generalization of Large Language Models","created":"2024-02-29","cited_by_count":27},{"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":"2408.01866","title":"Efficient Solutions For An Intriguing Failure of LLMs: Long Context Window Does Not Mean LLMs Can Analyze Long Sequences Flawlessly","created":"2024-08-03","cited_by_count":24},{"id":"2409.00509","title":"LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models","created":"2024-08-31","cited_by_count":23},{"id":"2405.03939","title":"Long Context Alignment with Short Instructions and Synthesized Positions","created":"2024-05-07","cited_by_count":22},{"id":"2402.13934","title":"Do Efficient Transformers Really Save Computation?","created":"2024-02-21","cited_by_count":20},{"id":"2406.00605","title":"LongSkywork: A Training Recipe for Efficiently Extending Context Length in Large Language Models","created":"2024-06-02","cited_by_count":19},{"id":"2312.17296","title":"Structured Packing in LLM Training Improves Long Context Utilization","created":"2023-12-28","cited_by_count":17},{"id":"2406.19598","title":"Mixture of In-Context Experts Enhance LLMs' Long Context Awareness","created":"2024-06-28","cited_by_count":17},{"id":"2405.19846","title":"Quest: Query-centric Data Synthesis Approach for Long-context Scaling of Large Language Model","created":"2024-05-30","cited_by_count":16},{"id":"2304.07547","title":"TagCLIP: Improving Discrimination Ability of Open-Vocabulary Semantic Segmentation","created":"2023-04-15","cited_by_count":14},{"id":"2406.09897","title":"3D-RPE: Enhancing Long-Context Modeling Through 3D Rotary Position Encoding","created":"2024-06-14","cited_by_count":13},{"id":"2409.06679","title":"E2LLM: Encoder Elongated Large Language Models for Long-Context Understanding and Reasoning","created":"2024-09-10","cited_by_count":13},{"id":"2401.06951","title":"E^2-LLM: Efficient and Extreme Length Extension of Large Language Models","created":"2024-01-13","cited_by_count":11},{"id":"2406.01895","title":"Explicitly Encoding Structural Symmetry is Key to Length Generalization in Arithmetic Tasks","created":"2024-06-04","cited_by_count":11},{"id":"2407.13739","title":"Scaling Granite Code Models to 128K Context","created":"2024-07-18","cited_by_count":11}],"next_cursor":"100"}