{"list":"other","total":51,"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":"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":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"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":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"2209.07753","title":"Code as Policies: Language Model Programs for Embodied Control","created":"2022-09-16","cited_by_count":1210},{"id":"2201.07207","title":"Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents","created":"2022-01-18","cited_by_count":1035},{"id":"2007.15779","title":"Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing","created":"2020-07-31","cited_by_count":1009},{"id":"1904.03323","title":"Publicly Available Clinical BERT Embeddings","created":"2019-04-06","cited_by_count":1002},{"id":"2209.05451","title":"Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation","created":"2022-09-12","cited_by_count":551},{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513},{"id":"2204.05999","title":"InCoder: A Generative Model for Code Infilling and Synthesis","created":"2022-04-12","cited_by_count":498},{"id":"2207.04429","title":"LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action","created":"2022-07-10","cited_by_count":439},{"id":"1803.08024","title":"Stacked Cross Attention for Image-Text Matching","created":"2018-03-21","cited_by_count":416},{"id":"2202.01771","title":"Pre-Trained Language Models for Interactive Decision-Making","created":"2022-02-03","cited_by_count":221},{"id":"1809.07041","title":"Exploring Visual Relationship for Image Captioning","created":"2018-09-19","cited_by_count":215},{"id":"2111.09888","title":"Simple but Effective: CLIP Embeddings for Embodied AI","created":"2021-11-18","cited_by_count":191},{"id":"2003.00392","title":"Fine-grained Video-Text Retrieval with Hierarchical Graph Reasoning","created":"2020-03-01","cited_by_count":180},{"id":"1808.00158","title":"Speaker Recognition from Raw Waveform with SincNet","created":"2018-07-29","cited_by_count":166},{"id":"2004.13701","title":"Deep Learning for ECG Analysis: Benchmarks and Insights from PTB-XL","created":"2020-04-28","cited_by_count":158},{"id":"1810.07212","title":"Cross-Modal and Hierarchical Modeling of Video and Text","created":"2018-10-16","cited_by_count":103},{"id":"2108.09980","title":"TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment","created":"2021-08-23","cited_by_count":102},{"id":"1908.03477","title":"Fine-Grained Action Retrieval Through Multiple Parts-of-Speech Embeddings","created":"2019-08-09","cited_by_count":101},{"id":"2106.11170","title":"Transformer-based Spatial-Temporal Feature Learning for EEG Decoding","created":"2021-06-11","cited_by_count":97},{"id":"2001.05295","title":"Language Models Are An Effective Patient Representation Learning Technique For Electronic Health Record Data","created":"2020-01-06","cited_by_count":87},{"id":"2204.11134","title":"Can Foundation Models Perform Zero-Shot Task Specification For Robot Manipulation?","created":"2022-04-23","cited_by_count":70},{"id":"1610.02947","title":"End-to-end Concept Word Detection for Video Captioning, Retrieval, and Question Answering","created":"2016-10-10","cited_by_count":60},{"id":"2205.10712","title":"Housekeep: Tidying Virtual Households using Commonsense Reasoning","created":"2022-05-22","cited_by_count":57},{"id":"2204.05080","title":"Semantic Exploration from Language Abstractions and Pretrained Representations","created":"2022-04-08","cited_by_count":51},{"id":"2106.00188","title":"PIGLeT: Language Grounding Through Neuro-Symbolic Interaction in a 3D World","created":"2021-06-01","cited_by_count":47},{"id":"1609.08124","title":"Learning Language-Visual Embedding for Movie Understanding with Natural-Language","created":"2016-09-26","cited_by_count":41},{"id":"2109.08908","title":"Intra-Inter Subject Self-supervised Learning for Multivariate Cardiac Signals","created":"2021-09-18","cited_by_count":35},{"id":"2108.09737","title":"A Transformer Architecture for Stress Detection from ECG","created":"2021-08-22","cited_by_count":27},{"id":"2206.13074","title":"Leveraging Language for Accelerated Learning of Tool Manipulation","created":"2022-06-27","cited_by_count":26},{"id":"2207.02442","title":"Transformers are Adaptable Task Planners","created":"2022-07-06","cited_by_count":15},{"id":"2110.15803","title":"Natural Language Processing for Smart Healthcare","created":"2021-10-19","cited_by_count":14},{"id":"2102.08655","title":"Decoding EEG Brain Activity for Multi-Modal Natural Language Processing","created":"2021-02-17","cited_by_count":13},{"id":"2208.06348","title":"Can Brain Signals Reveal Inner Alignment with Human Languages?","created":"2022-08-10","cited_by_count":12},{"id":"1908.05349","title":"Multimodal Emotion Recognition Using Deep Canonical Correlation Analysis","created":"2019-08-13","cited_by_count":10},{"id":"2010.05379","title":"MAF: Multimodal Alignment Framework for Weakly-Supervised Phrase Grounding","created":"2020-10-12","cited_by_count":9},{"id":"2208.01220","title":"GeoECG: Data Augmentation via Wasserstein Geodesic Perturbation for Robust Electrocardiogram Prediction","created":"2022-08-02","cited_by_count":8},{"id":"2204.03734","title":"MHMS: Multimodal Hierarchical Multimedia Summarization","created":"2022-04-07","cited_by_count":6},{"id":"2210.04722","title":"Semantics-Consistent Cross-domain Summarization via Optimal Transport Alignment","created":"2022-10-10","cited_by_count":6},{"id":"2210.05840","title":"LiveSeg: Unsupervised Multimodal Temporal Segmentation of Long Livestream Videos","created":"2022-10-12","cited_by_count":6},{"id":"1812.00475","title":"Multiple Instance Learning for ECG Risk Stratification","created":"2018-12-02","cited_by_count":5}],"next_cursor":null}