{"list":"other","total":63,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1603.02754","title":"XGBoost: A Scalable Tree Boosting System","created":"2016-03-09","cited_by_count":5166},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"1911.02685","title":"A Comprehensive Survey on Transfer Learning","created":"2019-11-07","cited_by_count":1160},{"id":"2205.05638","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","created":"2022-05-11","cited_by_count":896},{"id":"2106.11959","title":"Revisiting Deep Learning Models for Tabular Data","created":"2021-06-22","cited_by_count":740},{"id":"2308.03281","title":"Towards General Text Embeddings with Multi-stage Contrastive Learning","created":"2023-08-07","cited_by_count":723},{"id":"2305.03111","title":"Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs","created":"2023-05-04","cited_by_count":688},{"id":"2207.01848","title":"TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second","created":"2022-07-05","cited_by_count":674},{"id":"1908.07442","title":"TabNet: Attentive Interpretable Tabular Learning","created":"2019-08-20","cited_by_count":648},{"id":"2210.07316","title":"MTEB: Massive Text Embedding Benchmark","created":"2022-10-13","cited_by_count":640},{"id":"2106.03253","title":"Tabular Data: Deep Learning is Not All You Need","created":"2021-06-06","cited_by_count":535},{"id":"2110.01889","title":"Deep Neural Networks and Tabular Data: A Survey","created":"2021-10-05","cited_by_count":491},{"id":"2012.06678","title":"TabTransformer: Tabular Data Modeling Using Contextual Embeddings","created":"2020-12-11","cited_by_count":409},{"id":"2105.11447","title":"True Few-Shot Learning with Language Models","created":"2021-05-24","cited_by_count":344},{"id":"2109.01247","title":"Do Prompt-Based Models Really Understand the Meaning of their Prompts?","created":"2021-09-02","cited_by_count":326},{"id":"2106.01342","title":"SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training","created":"2021-06-02","cited_by_count":319},{"id":"2210.10723","title":"TabLLM: Few-shot Classification of Tabular Data with Large Language Models","created":"2022-10-19","cited_by_count":277},{"id":"2303.05398","title":"MathPrompter: Mathematical Reasoning using Large Language Models","created":"2023-03-04","cited_by_count":236},{"id":"1909.06312","title":"Neural Oblivious Decision Ensembles for Deep Learning on Tabular Data","created":"2019-09-13","cited_by_count":203},{"id":"2203.05556","title":"On Embeddings for Numerical Features in Tabular Deep Learning","created":"2022-03-10","cited_by_count":186},{"id":"2310.03731","title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","created":"2023-10-05","cited_by_count":156},{"id":"2106.11189","title":"Well-tuned Simple Nets Excel on Tabular Datasets","created":"2021-06-21","cited_by_count":151},{"id":"2206.06565","title":"LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks","created":"2022-06-14","cited_by_count":148},{"id":"2104.04670","title":"Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collections","created":"2021-04-10","cited_by_count":128},{"id":"2305.13062","title":"Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Study","created":"2023-05-22","cited_by_count":116},{"id":"2206.06602","title":"Deep Isolation Forest for Anomaly Detection","created":"2022-06-14","cited_by_count":92},{"id":"2312.07577","title":"Benchmarking Distribution Shift in Tabular Data with TableShift","created":"2023-12-10","cited_by_count":66},{"id":"2401.06866","title":"Health-LLM: Large Language Models for Health Prediction via Wearable Sensor Data","created":"2024-01-12","cited_by_count":66},{"id":"2206.15306","title":"Transfer Learning with Deep Tabular Models","created":"2022-06-30","cited_by_count":52},{"id":"2307.09018","title":"Multimodal LLMs for health grounded in individual-specific data","created":"2023-07-18","cited_by_count":49},{"id":"1705.08963","title":"DeepSecure: Scalable Provably-Secure Deep Learning","created":"2017-05-24","cited_by_count":48},{"id":"2403.07384","title":"SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models","created":"2024-03-12","cited_by_count":44},{"id":"1903.11314","title":"Scalable Deep Learning on Distributed Infrastructures: Challenges, Techniques and Tools","created":"2019-03-27","cited_by_count":40},{"id":"2310.02989","title":"xVal: A Continuous Numerical Tokenization for Scientific Language Models","created":"2023-10-04","cited_by_count":27},{"id":"2310.07338","title":"From Supervised to Generative: A Novel Paradigm for Tabular Deep Learning with Large Language Models","created":"2023-10-11","cited_by_count":24},{"id":"2311.04937","title":"Multimodal Clinical Benchmark for Emergency Care (MC-BEC): A Comprehensive Benchmark for Evaluating Foundation Models in Emergency Medicine","created":"2023-11-07","cited_by_count":24},{"id":"2402.12869","title":"Exploring the Impact of Table-to-Text Methods on Augmenting LLM-based Question Answering with Domain Hybrid Data","created":"2024-02-20","cited_by_count":24},{"id":"2402.18439","title":"Beyond Natural Language: LLMs Leveraging Alternative Formats for Enhanced Reasoning and Communication","created":"2024-02-28","cited_by_count":14},{"id":"1807.02757","title":"Fringe pattern analysis using deep learning","created":"2018-07-08","cited_by_count":13},{"id":"2312.12464","title":"Towards Better Serialization of Tabular Data for Few-shot Classification with Large Language Models","created":"2023-12-18","cited_by_count":12},{"id":"1905.08509","title":"Mutual Information Maximization in Graph Neural Networks","created":"2019-05-21","cited_by_count":9},{"id":"2405.20419","title":"Enhancing Antibiotic Stewardship using a Natural Language Approach for Better Feature Representation","created":"2024-05-30","cited_by_count":8},{"id":"2402.15422","title":"A Data-Centric Approach To Generate Faithful and High Quality Patient Summaries with Large Language Models","created":"2024-02-23","cited_by_count":6},{"id":"1811.10658","title":"HELOC Applicant Risk Performance Evaluation by Topological Hierarchical Decomposition","created":"2018-11-26","cited_by_count":5},{"id":"2106.05239","title":"XBNet : An Extremely Boosted Neural Network","created":"2021-06-09","cited_by_count":5},{"id":"2010.04524","title":"Multi-Objective Optimisation of Multi-Output Neural Trees","created":"2020-10-09","cited_by_count":2},{"id":"2310.09049","title":"SAI: Solving AI Tasks with Systematic Artificial Intelligence in Communication Network","created":"2023-10-13","cited_by_count":1}],"next_cursor":null}