{"total":117,"rows":[{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780,"area":null},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234,"area":null},{"id":"2104.08786","title":"Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity","created":"2021-04-18","cited_by_count":1135,"area":null},{"id":"2212.12017","title":"OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization","created":"2022-12-22","cited_by_count":236,"area":null},{"id":"2102.09550","title":"Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer","created":"2021-02-18","cited_by_count":134,"area":null},{"id":"2101.09459","title":"Advances and Challenges in Conversational Recommender Systems: A Survey","created":"2021-01-23","cited_by_count":118,"area":null},{"id":"2203.16761","title":"MeMOT: Multi-Object Tracking with Memory","created":"2022-03-31","cited_by_count":114,"area":null},{"id":"2205.12674","title":"Training Language Models with Memory Augmentation","created":"2022-05-25","cited_by_count":113,"area":null},{"id":"2103.04224","title":"MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detection","created":"2021-03-07","cited_by_count":106,"area":null},{"id":"2110.07298","title":"LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5","created":"2021-10-14","cited_by_count":104,"area":null},{"id":"2305.02437","title":"Lift Yourself Up: Retrieval-augmented Text Generation with Self Memory","created":"2023-05-03","cited_by_count":103,"area":"rag"},{"id":"2104.00324","title":"STMTrack: Template-free Visual Tracking with Space-time Memory Networks","created":"2021-04-01","cited_by_count":91,"area":null},{"id":"2203.11474","title":"Remember Intentions: Retrospective-Memory-based Trajectory Prediction","created":"2022-03-22","cited_by_count":86,"area":null},{"id":"2109.11404","title":"Hierarchical Memory Matching Network for Video Object Segmentation","created":"2021-09-23","cited_by_count":72,"area":null},{"id":"2112.00061","title":"Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resources","created":"2021-11-30","cited_by_count":71,"area":null},{"id":"2310.07064","title":"Large Language Models can Learn Rules","created":"2023-10-10","cited_by_count":69,"area":null},{"id":"2203.16797","title":"When Physics Meets Machine Learning: A Survey of Physics-Informed Machine Learning","created":"2022-03-31","cited_by_count":65,"area":null},{"id":"2402.05391","title":"Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey","created":"2024-02-08","cited_by_count":53,"area":null},{"id":"2103.16775","title":"Attention, please! A survey of Neural Attention Models in Deep Learning","created":"2021-03-31","cited_by_count":51,"area":null},{"id":"2104.00902","title":"HVPR: Hybrid Voxel-Point Representation for Single-stage 3D Object Detection","created":"2021-04-02","cited_by_count":47,"area":null},{"id":"2111.04318","title":"Auto-Encoding Knowledge Graph for Unsupervised Medical Report Generation","created":"2021-11-08","cited_by_count":47,"area":null},{"id":"2104.00743","title":"Towards General Purpose Vision Systems","created":"2021-04-01","cited_by_count":46,"area":null},{"id":"2111.13495","title":"SQUID: Deep Feature In-Painting for Unsupervised Anomaly Detection","created":"2021-11-26","cited_by_count":34,"area":null},{"id":"2203.07931","title":"DialogueNeRF: Towards Realistic Avatar Face-to-Face Conversation Video Generation","created":"2022-03-15","cited_by_count":30,"area":null},{"id":"2202.11822","title":"Using natural language prompts for machine translation","created":"2022-02-23","cited_by_count":27,"area":null},{"id":"2205.07557","title":"Heroes, Villains, and Victims, and GPT-3: Automated Extraction of Character Roles Without Training Data","created":"2022-05-16","cited_by_count":27,"area":null},{"id":"2403.12776","title":"Automated Data Curation for Robust Language Model Fine-Tuning","created":"2024-03-19","cited_by_count":27,"area":null},{"id":"2203.12446","title":"SMEMO: Social Memory for Trajectory Forecasting","created":"2022-03-23","cited_by_count":26,"area":null},{"id":"2302.11087","title":"A Survey on User Behavior Modeling in Recommender Systems","created":"2023-02-22","cited_by_count":26,"area":null},{"id":"2312.02530","title":"MEMTO: Memory-guided Transformer for Multivariate Time Series Anomaly Detection","created":"2023-12-05","cited_by_count":26,"area":null},{"id":"2311.00308","title":"From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities","created":"2023-11-01","cited_by_count":25,"area":null},{"id":"2307.14336","title":"MAMo: Leveraging Memory and Attention for Monocular Video Depth Estimation","created":"2023-07-26","cited_by_count":24,"area":null},{"id":"2108.07502","title":"MV-TON: Memory-based Video Virtual Try-on network","created":"2021-08-17","cited_by_count":23,"area":null},{"id":"2212.05005","title":"Memories are One-to-Many Mapping Alleviators in Talking Face Generation","created":"2022-12-09","cited_by_count":22,"area":null},{"id":"2104.05170","title":"Memory-guided Unsupervised Image-to-image Translation","created":"2021-04-12","cited_by_count":21,"area":null},{"id":"2110.03192","title":"GNN is a Counter? Revisiting GNN for Question Answering","created":"2021-10-07","cited_by_count":21,"area":null},{"id":"2307.12058","title":"Discovering Spatio-Temporal Rationales for Video Question Answering","created":"2023-07-22","cited_by_count":21,"area":null},{"id":"2209.12441","title":"Visual Anomaly Detection Via Partition Memory Bank Module and Error Estimation","created":"2022-09-26","cited_by_count":20,"area":null},{"id":"2110.04374","title":"A Few More Examples May Be Worth Billions of Parameters","created":"2021-10-08","cited_by_count":19,"area":null},{"id":"2104.10640","title":"The NLP Cookbook: Modern Recipes for Transformer based Deep Learning Architectures","created":"2021-03-23","cited_by_count":16,"area":null},{"id":"2206.04045","title":"STable: Table Generation Framework for Encoder-Decoder Models","created":"2022-06-08","cited_by_count":15,"area":null},{"id":"2207.14000","title":"Multi-Step Deductive Reasoning Over Natural Language: An Empirical Study on Out-of-Distribution Generalisation","created":"2022-07-28","cited_by_count":15,"area":"lr"},{"id":"2107.01671","title":"Cognitive Visual Commonsense Reasoning Using Dynamic Working Memory","created":"2021-07-04","cited_by_count":14,"area":null},{"id":"2212.13296","title":"VQA and Visual Reasoning: An Overview of Recent Datasets, Methods and Challenges","created":"2022-12-26","cited_by_count":14,"area":"lr"},{"id":"2101.09704","title":"Does Head Label Help for Long-Tailed Multi-Label Text Classification","created":"2021-01-24","cited_by_count":13,"area":null},{"id":"2105.09509","title":"Adaptive Knowledge-Enhanced Bayesian Meta-Learning for Few-shot Event Detection","created":"2021-05-20","cited_by_count":13,"area":null},{"id":"2311.03498","title":"In-Context Exemplars as Clues to Retrieving from Large Associative Memory","created":"2023-11-06","cited_by_count":13,"area":null},{"id":"2403.08689","title":"Exploiting Structural Consistency of Chest Anatomy for Unsupervised Anomaly Detection in Radiography Images","created":"2024-03-13","cited_by_count":13,"area":null},{"id":"2101.11707","title":"Knowledge-driven Natural Language Understanding of English Text and its Applications","created":"2021-01-27","cited_by_count":12,"area":null},{"id":"2208.00946","title":"Motion-aware Memory Network for Fast Video Salient Object Detection","created":"2022-08-01","cited_by_count":12,"area":null},{"id":"2106.14269","title":"Deep Learning for Technical Document Classification","created":"2021-06-27","cited_by_count":11,"area":null},{"id":"2109.10480","title":"DialogueBERT: A Self-Supervised Learning based Dialogue Pre-training Encoder","created":"2021-09-22","cited_by_count":11,"area":null},{"id":"2206.11229","title":"Business Document Information Extraction: Towards Practical Benchmarks","created":"2022-06-20","cited_by_count":11,"area":null},{"id":"2302.09236","title":"Scalable Prompt Generation for Semi-supervised Learning with Language Models","created":"2023-02-18","cited_by_count":11,"area":null},{"id":"2309.15251","title":"VPA: Fully Test-Time Visual Prompt Adaptation","created":"2023-09-26","cited_by_count":11,"area":null},{"id":"2407.12982","title":"Retrieval-Enhanced Machine Learning: Synthesis and Opportunities","created":"2024-07-17","cited_by_count":11,"area":null},{"id":"2104.00772","title":"Low-Resource Language Modelling of South African Languages","created":"2021-04-01","cited_by_count":10,"area":null},{"id":"2204.04637","title":"UniDU: Towards A Unified Generative Dialogue Understanding Framework","created":"2022-04-10","cited_by_count":9,"area":null},{"id":"2301.06745","title":"BERT-ERC: Fine-tuning BERT is Enough for Emotion Recognition in Conversation","created":"2023-01-17","cited_by_count":9,"area":null},{"id":"2104.02899","title":"Recognizing and Verifying Mathematical Equations using Multiplicative Differential Neural Units","created":"2021-04-07","cited_by_count":8,"area":null},{"id":"2109.13392","title":"The Tensor Brain: A Unified Theory of Perception, Memory and Semantic Decoding","created":"2021-09-27","cited_by_count":8,"area":null},{"id":"2112.05909","title":"Neural Attention Models in Deep Learning: Survey and Taxonomy","created":"2021-12-11","cited_by_count":8,"area":null},{"id":"2210.06466","title":"Prompt Generation Networks for Input-Space Adaptation of Frozen Vision Transformers","created":"2022-10-12","cited_by_count":8,"area":null},{"id":"2506.06599","title":"Direct Prediction Set Minimization via Bilevel Conformal Classifier Training","created":"2025-06-07","cited_by_count":8,"area":null},{"id":"2304.06018","title":"Adaptive Human Matting for Dynamic Videos","created":"2023-04-12","cited_by_count":7,"area":null},{"id":"2110.11337","title":"Empowering General-purpose User Representation with Full-life Cycle Behavior Modeling","created":"2021-10-20","cited_by_count":6,"area":null},{"id":"2111.11520","title":"Zero-Shot Open-Book Question Answering","created":"2021-11-22","cited_by_count":6,"area":null},{"id":"2204.14264","title":"Polyglot Prompt: Multilingual Multitask PrompTraining","created":"2022-04-29","cited_by_count":6,"area":null},{"id":"2301.00867","title":"Follow the Timeline! Generating Abstractive and Extractive Timeline Summary in Chronological Order","created":"2023-01-02","cited_by_count":6,"area":null},{"id":"2105.07957","title":"Evolutionary Training and Abstraction Yields Algorithmic Generalization of Neural Computers","created":"2021-05-17","cited_by_count":5,"area":null},{"id":"2209.12617","title":"Evaluation of Question Answering Systems: Complexity of judging a natural language","created":"2022-09-10","cited_by_count":5,"area":null},{"id":"2211.07625","title":"What Images are More Memorable to Machines?","created":"2022-11-14","cited_by_count":5,"area":null},{"id":"2304.04874","title":"ImageCaptioner$^2$: Image Captioner for Image Captioning Bias Amplification Assessment","created":"2023-04-10","cited_by_count":5,"area":null},{"id":"2408.09422","title":"Distinguish Confusion in Legal Judgment Prediction via Revised Relation Knowledge","created":"2024-08-18","cited_by_count":5,"area":null},{"id":"2510.21887","title":"Generative AI in Depth: A Survey of Recent Advances, Model Variants, and Real-World Applications","created":"2025-10-23","cited_by_count":5,"area":"diffusion"},{"id":"2106.10686","title":"Quality-Aware Memory Network for Interactive Volumetric Image Segmentation","created":"2021-06-20","cited_by_count":4,"area":null},{"id":"2111.07602","title":"Spectral Transform Forms Scalable Transformer","created":"2021-11-15","cited_by_count":4,"area":null},{"id":"2303.04998","title":"Rethinking Visual Prompt Learning as Masked Visual Token Modeling","created":"2023-03-09","cited_by_count":4,"area":null},{"id":"2401.02916","title":"Uncovering the human motion pattern: Pattern Memory-based Diffusion Model for Trajectory Prediction","created":"2024-01-05","cited_by_count":4,"area":"diffusion"},{"id":"1805.04969","title":"Learning Temporal Strategic Relationships using Generative Adversarial Imitation Learning","created":"2018-05-13","cited_by_count":3,"area":"offlinerl"},{"id":"2208.04022","title":"Sparse Attentive Memory Network for Click-through Rate Prediction with Long Sequences","created":"2022-08-08","cited_by_count":3,"area":null},{"id":"2307.10768","title":"Decoding the Enigma: Benchmarking Humans and AIs on the Many Facets of Working Memory","created":"2023-07-20","cited_by_count":3,"area":null},{"id":"2206.07762","title":"Physics-Infused Fuzzy Generative Adversarial Network for Robust Failure Prognosis","created":"2022-06-15","cited_by_count":2,"area":null},{"id":"2301.02809","title":"A Brain-inspired Memory Transformation based Differentiable Neural Computer for Reasoning-based Question Answering","created":"2023-01-07","cited_by_count":2,"area":null},{"id":"2306.06371","title":"A Comprehensive Review of State-of-The-Art Methods for Java Code Generation from Natural Language Text","created":"2023-06-10","cited_by_count":2,"area":null},{"id":"2307.11709","title":"Statement-based Memory for Neural Source Code Summarization","created":"2023-07-21","cited_by_count":2,"area":null},{"id":"2410.01816","title":"Automatic Scene Generation: State-of-the-Art Techniques, Models, Datasets, Challenges, and Future Prospects","created":"2024-09-14","cited_by_count":2,"area":null},{"id":"2506.06806","title":"Label-semantics Aware Generative Approach for Domain-Agnostic Multilabel Classification","created":"2025-06-07","cited_by_count":2,"area":null},{"id":"2103.16795","title":"Multi-Class Multi-Instance Count Conditioned Adversarial Image Generation","created":"2021-03-31","cited_by_count":1,"area":null},{"id":"2105.00357","title":"RotLSTM: Rotating Memories in Recurrent Neural Networks","created":"2021-05-01","cited_by_count":1,"area":null},{"id":"2106.01440","title":"Memory Wrap: a Data-Efficient and Interpretable Extension to Image Classification Models","created":"2021-06-01","cited_by_count":1,"area":null},{"id":"2110.11284","title":"Multi-Object Tracking and Segmentation with a Space-Time Memory Network","created":"2021-10-21","cited_by_count":1,"area":null},{"id":"2304.07022","title":"Label Dependencies-aware Set Prediction Networks for Multi-label Text Classification","created":"2023-04-14","cited_by_count":1,"area":null},{"id":"2307.15679","title":"Dynamic Analysis and an Eigen Initializer for Recurrent Neural Networks","created":"2023-07-28","cited_by_count":1,"area":null},{"id":"2307.15694","title":"Universal Recurrent Event Memories for Streaming Data","created":"2023-07-28","cited_by_count":1,"area":null},{"id":"2308.02558","title":"The Paradigm Shifts in Artificial Intelligence","created":"2023-08-02","cited_by_count":1,"area":null},{"id":"2309.09179","title":"Syntax Tree Constrained Graph Network for Visual Question Answering","created":"2023-09-17","cited_by_count":1,"area":null},{"id":"2408.03841","title":"MaxMind: A Memory Loop Network to Enhance Software Productivity based on Large Language Models","created":"2024-08-07","cited_by_count":1,"area":null},{"id":"2412.15673","title":"Learning Group Interactions and Semantic Intentions for Multi-Object Trajectory Prediction","created":"2024-12-20","cited_by_count":1,"area":null},{"id":"2505.16756","title":"Representation Discrepancy Bridging Method for Remote Sensing Image-Text Retrieval","created":"2025-05-22","cited_by_count":1,"area":null}],"next_cursor":"100"}