{"total":296,"rows":[{"id":"2210.02414","title":"GLM-130B: An Open Bilingual Pre-trained Model","created":"2022-10-05","cited_by_count":843,"area":null},{"id":"2310.10688","title":"A decoder-only foundation model for time-series forecasting","created":"2023-10-14","cited_by_count":692,"area":null},{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648,"area":null},{"id":"2106.04554","title":"A Survey of Transformers","created":"2021-06-08","cited_by_count":401,"area":null},{"id":"2304.08467","title":"Learning to Compress Prompts with Gist Tokens","created":"2023-04-17","cited_by_count":390,"area":null},{"id":"2103.02143","title":"Random Feature Attention","created":"2021-03-03","cited_by_count":354,"area":null},{"id":"2105.03824","title":"FNet: Mixing Tokens with Fourier Transforms","created":"2021-05-09","cited_by_count":347,"area":null},{"id":"2104.02112","title":"Efficient Attentions for Long Document Summarization","created":"2021-04-05","cited_by_count":345,"area":null},{"id":"2205.05131","title":"UL2: Unifying Language Learning Paradigms","created":"2022-05-10","cited_by_count":295,"area":null},{"id":"2109.10862","title":"Recursively Summarizing Books with Human Feedback","created":"2021-09-22","cited_by_count":290,"area":null},{"id":"2102.01672","title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","created":"2021-02-02","cited_by_count":239,"area":null},{"id":"2204.06092","title":"ASQA: Factoid Questions Meet Long-Form Answers","created":"2022-04-12","cited_by_count":234,"area":null},{"id":"2301.04558","title":"Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing","created":"2023-01-11","cited_by_count":211,"area":null},{"id":"2302.10724","title":"ChatGPT: Jack of all trades, master of none","created":"2023-02-21","cited_by_count":204,"area":null},{"id":"2209.15558","title":"Out-of-Distribution Detection and Selective Generation for Conditional Language Models","created":"2022-09-30","cited_by_count":197,"area":null},{"id":"2309.14322","title":"Small-scale proxies for large-scale Transformer training instabilities","created":"2023-09-25","cited_by_count":183,"area":null},{"id":"2402.18013","title":"A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems","created":"2024-02-28","cited_by_count":170,"area":null},{"id":"2103.06332","title":"Hurdles to Progress in Long-form Question Answering","created":"2021-03-10","cited_by_count":167,"area":null},{"id":"2402.14207","title":"Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models","created":"2024-02-22","cited_by_count":154,"area":null},{"id":"2204.05832","title":"What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization?","created":"2022-04-12","cited_by_count":150,"area":null},{"id":"2110.10090","title":"Inductive Biases and Variable Creation in Self-Attention Mechanisms","created":"2021-10-19","cited_by_count":144,"area":null},{"id":"2305.01625","title":"Unlimiformer: Long-Range Transformers with Unlimited Length Input","created":"2023-05-02","cited_by_count":128,"area":null},{"id":"2403.09636","title":"Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference","created":"2024-03-14","cited_by_count":116,"area":null},{"id":"2305.11487","title":"PointGPT: Auto-regressively Generative Pre-training from Point Clouds","created":"2023-05-19","cited_by_count":115,"area":null},{"id":"2310.03025","title":"Retrieval meets Long Context Large Language Models","created":"2023-10-04","cited_by_count":115,"area":null},{"id":"2205.12674","title":"Training Language Models with Memory Augmentation","created":"2022-05-25","cited_by_count":113,"area":null},{"id":"2201.10326","title":"ShapeFormer: Transformer-based Shape Completion via Sparse Representation","created":"2022-01-25","cited_by_count":106,"area":null},{"id":"2401.12926","title":"DsDm: Model-Aware Dataset Selection with Datamodels","created":"2024-01-23","cited_by_count":105,"area":null},{"id":"2103.13076","title":"Finetuning Pretrained Transformers into RNNs","created":"2021-03-24","cited_by_count":96,"area":null},{"id":"2106.01540","title":"Luna: Linear Unified Nested Attention","created":"2021-06-03","cited_by_count":96,"area":null},{"id":"2108.08771","title":"Learning to Match Features with Seeded Graph Matching Network","created":"2021-08-19","cited_by_count":92,"area":null},{"id":"2210.15424","title":"What Language Model to Train if You Have One Million GPU Hours?","created":"2022-10-27","cited_by_count":92,"area":null},{"id":"2301.01767","title":"Self-Supervised Video Forensics by Audio-Visual Anomaly Detection","created":"2023-01-04","cited_by_count":85,"area":null},{"id":"2310.07707","title":"MatFormer: Nested Transformer for Elastic Inference","created":"2023-10-11","cited_by_count":85,"area":null},{"id":"2104.06486","title":"MS2: Multi-Document Summarization of Medical Studies","created":"2021-04-13","cited_by_count":80,"area":null},{"id":"2104.07091","title":"SummScreen: A Dataset for Abstractive Screenplay Summarization","created":"2021-04-14","cited_by_count":79,"area":null},{"id":"2202.07371","title":"Personalized Prompt Learning for Explainable Recommendation","created":"2022-02-15","cited_by_count":79,"area":null},{"id":"2207.00939","title":"An Empirical Survey on Long Document Summarization: Datasets, Models and Metrics","created":"2022-07-03","cited_by_count":74,"area":null},{"id":"2110.03860","title":"Token Pooling in Vision Transformers","created":"2021-10-08","cited_by_count":69,"area":null},{"id":"2106.00515","title":"KVT: k-NN Attention for Boosting Vision Transformers","created":"2021-05-28","cited_by_count":65,"area":null},{"id":"2207.09161","title":"Single Stage Virtual Try-on via Deformable Attention Flows","created":"2022-07-19","cited_by_count":65,"area":null},{"id":"2110.08499","title":"PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization","created":"2021-10-16","cited_by_count":62,"area":null},{"id":"2105.04371","title":"Poolingformer: Long Document Modeling with Pooling Attention","created":"2021-05-10","cited_by_count":60,"area":null},{"id":"2202.07765","title":"General-purpose, long-context autoregressive modeling with Perceiver AR","created":"2022-02-15","cited_by_count":60,"area":null},{"id":"2105.11601","title":"Personalized Transformer for Explainable Recommendation","created":"2021-05-25","cited_by_count":59,"area":null},{"id":"2304.08448","title":"An Iterative Optimizing Framework for Radiology Report Summarization with ChatGPT","created":"2023-04-17","cited_by_count":57,"area":null},{"id":"2304.14670","title":"Prompt Engineering for Healthcare: Methodologies and Applications","created":"2023-04-28","cited_by_count":52,"area":null},{"id":"2406.11289","title":"A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Models","created":"2024-06-17","cited_by_count":52,"area":null},{"id":"2307.12375","title":"In-Context Learning Learns Label Relationships but Is Not Conventional Learning","created":"2023-07-23","cited_by_count":51,"area":null},{"id":"2401.06199","title":"xTrimoPGLM: Unified 100B-Scale Pre-trained Transformer for Deciphering the Language of Protein","created":"2024-01-11","cited_by_count":50,"area":null},{"id":"2305.19268","title":"Intriguing Properties of Quantization at Scale","created":"2023-05-30","cited_by_count":49,"area":null},{"id":"2309.09369","title":"Embrace Divergence for Richer Insights: A Multi-document Summarization Benchmark and a Case Study on Summarizing Diverse Information from News Articles","created":"2023-09-17","cited_by_count":45,"area":null},{"id":"2112.07637","title":"Exploring Neural Models for Query-Focused Summarization","created":"2021-12-14","cited_by_count":44,"area":null},{"id":"2207.00397","title":"Conditional Generation with a Question-Answering Blueprint","created":"2022-07-01","cited_by_count":44,"area":null},{"id":"2304.04052","title":"Decoder-Only or Encoder-Decoder? Interpreting Language Model as a Regularized Encoder-Decoder","created":"2023-04-08","cited_by_count":44,"area":null},{"id":"2312.14820","title":"How Smooth Is Attention?","created":"2023-12-22","cited_by_count":44,"area":null},{"id":"2211.12835","title":"Automatic Generation of Socratic Subquestions for Teaching Math Word Problems","created":"2022-11-23","cited_by_count":43,"area":null},{"id":"2201.05176","title":"Neural Approaches to Conversational Information Retrieval","created":"2022-01-13","cited_by_count":42,"area":null},{"id":"2107.06419","title":"FLAT: An Optimized Dataflow for Mitigating Attention Bottlenecks","created":"2021-07-13","cited_by_count":39,"area":null},{"id":"2112.08634","title":"FRUIT: Faithfully Reflecting Updated Information in Text","created":"2021-12-16","cited_by_count":39,"area":null},{"id":"2302.04931","title":"In-Context Learning with Many Demonstration Examples","created":"2023-02-09","cited_by_count":39,"area":null},{"id":"2106.00829","title":"ConvoSumm: Conversation Summarization Benchmark and Improved Abstractive Summarization with Argument Mining","created":"2021-06-01","cited_by_count":38,"area":null},{"id":"2110.07752","title":"Hindsight: Posterior-guided training of retrievers for improved open-ended generation","created":"2021-10-14","cited_by_count":38,"area":null},{"id":"2202.00132","title":"Submodularity In Machine Learning and Artificial Intelligence","created":"2022-01-31","cited_by_count":38,"area":null},{"id":"2210.06640","title":"Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2110.02488","title":"ABC: Attention with Bounded-memory Control","created":"2021-10-06","cited_by_count":36,"area":null},{"id":"2202.09583","title":"Models and Datasets for Cross-Lingual Summarisation","created":"2022-02-19","cited_by_count":36,"area":null},{"id":"2105.00816","title":"What's in a Summary? Laying the Groundwork for Advances in Hospital-Course Summarization","created":"2021-04-12","cited_by_count":35,"area":null},{"id":"2410.24087","title":"In-Context Fine-Tuning for Time-Series Foundation Models","created":"2024-10-31","cited_by_count":35,"area":null},{"id":"2106.08556","title":"Coreference-Aware Dialogue Summarization","created":"2021-06-16","cited_by_count":34,"area":null},{"id":"2204.11786","title":"Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications","created":"2022-04-25","cited_by_count":32,"area":null},{"id":"2109.15142","title":"Redesigning the Transformer Architecture with Insights from Multi-particle Dynamical Systems","created":"2021-09-30","cited_by_count":31,"area":null},{"id":"2204.04667","title":"Linear Complexity Randomized Self-attention Mechanism","created":"2022-04-10","cited_by_count":31,"area":null},{"id":"2402.11139","title":"LiGNN: Graph Neural Networks at LinkedIn","created":"2024-02-17","cited_by_count":31,"area":null},{"id":"2109.04953","title":"Does Pretraining for Summarization Require Knowledge Transfer?","created":"2021-09-10","cited_by_count":30,"area":null},{"id":"2206.09755","title":"Square One Bias in NLP: Towards a Multi-Dimensional Exploration of the Research Manifold","created":"2022-06-20","cited_by_count":29,"area":null},{"id":"2304.04358","title":"WebBrain: Learning to Generate Factually Correct Articles for Queries by Grounding on Large Web Corpus","created":"2023-04-10","cited_by_count":29,"area":null},{"id":"2110.08678","title":"Improving Transformers with Probabilistic Attention Keys","created":"2021-10-16","cited_by_count":28,"area":null},{"id":"2207.06983","title":"Multitrack Music Transformer","created":"2022-07-14","cited_by_count":28,"area":null},{"id":"2108.13139","title":"CSDS: A Fine-Grained Chinese Dataset for Customer Service Dialogue Summarization","created":"2021-08-30","cited_by_count":27,"area":null},{"id":"2204.04902","title":"NeuS: Neutral Multi-News Summarization for Mitigating Framing Bias","created":"2022-04-11","cited_by_count":27,"area":null},{"id":"2305.01498","title":"Summarizing Multiple Documents with Conversational Structure for Meta-Review Generation","created":"2023-05-02","cited_by_count":27,"area":null},{"id":"2108.02347","title":"FMMformer: Efficient and Flexible Transformer via Decomposed Near-field and Far-field Attention","created":"2021-08-05","cited_by_count":26,"area":null},{"id":"2309.16354","title":"Transformer-VQ: Linear-Time Transformers via Vector Quantization","created":"2023-09-28","cited_by_count":26,"area":null},{"id":"2102.03340","title":"NRTSI: Non-Recurrent Time Series Imputation","created":"2021-02-05","cited_by_count":25,"area":null},{"id":"2103.00751","title":"Long Document Summarization in a Low Resource Setting using Pretrained Language Models","created":"2021-03-01","cited_by_count":24,"area":null},{"id":"2104.12714","title":"Focused Attention Improves Document-Grounded Generation","created":"2021-04-26","cited_by_count":24,"area":null},{"id":"2105.03801","title":"Long-Span Summarization via Local Attention and Content Selection","created":"2021-05-08","cited_by_count":24,"area":null},{"id":"2212.09233","title":"OASum: Large-Scale Open Domain Aspect-based Summarization","created":"2022-12-19","cited_by_count":24,"area":null},{"id":"2303.16839","title":"MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks","created":"2023-03-29","cited_by_count":24,"area":null},{"id":"2110.10577","title":"Overview of the 2021 Key Point Analysis Shared Task","created":"2021-10-20","cited_by_count":23,"area":null},{"id":"2203.08436","title":"Don't Say What You Don't Know: Improving the Consistency of Abstractive Summarization by Constraining Beam Search","created":"2022-03-16","cited_by_count":23,"area":null},{"id":"2302.03815","title":"Long Text and Multi-Table Summarization: Dataset and Method","created":"2023-02-08","cited_by_count":23,"area":null},{"id":"2302.04542","title":"Efficient Attention via Control Variates","created":"2023-02-09","cited_by_count":23,"area":null},{"id":"2204.02213","title":"EntSUM: A Data Set for Entity-Centric Summarization","created":"2022-04-05","cited_by_count":22,"area":null},{"id":"2105.12041","title":"BASS: Boosting Abstractive Summarization with Unified Semantic Graph","created":"2021-05-25","cited_by_count":21,"area":null},{"id":"2212.10526","title":"Open Domain Multi-document Summarization: A Comprehensive Study of Model Brittleness under Retrieval","created":"2022-12-20","cited_by_count":20,"area":null},{"id":"2305.17026","title":"How Powerful are Decoder-Only Transformer Neural Models?","created":"2023-05-26","cited_by_count":20,"area":null},{"id":"2401.06532","title":"INTERS: Unlocking the Power of Large Language Models in Search with Instruction Tuning","created":"2024-01-12","cited_by_count":20,"area":null},{"id":"2104.13498","title":"Towards Clinical Encounter Summarization: Learning to Compose Discharge Summaries from Prior Notes","created":"2021-04-27","cited_by_count":19,"area":null}],"next_cursor":"100"}