{"total":1026,"rows":[{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509,"area":"moe"},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998,"area":null},{"id":"2503.19786","title":"Gemma 3 Technical Report","created":"2025-03-25","cited_by_count":1824,"area":null},{"id":"2103.07191","title":"Are NLP Models really able to Solve Simple Math Word Problems?","created":"2021-03-12","cited_by_count":878,"area":null},{"id":"2105.14491","title":"How Attentive are Graph Attention Networks?","created":"2021-05-30","cited_by_count":835,"area":null},{"id":"2209.11302","title":"ProgPrompt: Generating Situated Robot Task Plans using Large Language Models","created":"2022-09-22","cited_by_count":611,"area":null},{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459,"area":null},{"id":"2103.06333","title":"Unified Pre-training for Program Understanding and Generation","created":"2021-03-10","cited_by_count":366,"area":null},{"id":"2112.10482","title":"ScanQA: 3D Question Answering for Spatial Scene Understanding","created":"2021-12-20","cited_by_count":346,"area":null},{"id":"2103.14023","title":"AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting","created":"2021-03-25","cited_by_count":331,"area":null},{"id":"2205.13671","title":"Transformer for Partial Differential Equations' Operator Learning","created":"2022-05-26","cited_by_count":283,"area":null},{"id":"2104.05704","title":"Escaping the Big Data Paradigm with Compact Transformers","created":"2021-04-12","cited_by_count":264,"area":null},{"id":"2109.12894","title":"Training Spiking Neural Networks Using Lessons From Deep Learning","created":"2021-09-27","cited_by_count":259,"area":null},{"id":"2202.06417","title":"A Contrastive Framework for Neural Text Generation","created":"2022-02-13","cited_by_count":225,"area":null},{"id":"2101.08231","title":"Word Alignment by Fine-tuning Embeddings on Parallel Corpora","created":"2021-01-20","cited_by_count":186,"area":null},{"id":"2106.06981","title":"Thinking Like Transformers","created":"2021-06-13","cited_by_count":184,"area":null},{"id":"2202.02541","title":"TorchMD-NET: Equivariant Transformers for Neural Network based Molecular Potentials","created":"2022-02-05","cited_by_count":182,"area":null},{"id":"2105.12397","title":"Improving Sign Language Translation with Monolingual Data by Sign Back-Translation","created":"2021-05-26","cited_by_count":179,"area":null},{"id":"2209.10655","title":"Mega: Moving Average Equipped Gated Attention","created":"2022-09-21","cited_by_count":179,"area":null},{"id":"2311.01460","title":"Implicit Chain of Thought Reasoning via Knowledge Distillation","created":"2023-11-02","cited_by_count":176,"area":"lr"},{"id":"2108.11601","title":"Retrieval Augmented Code Generation and Summarization","created":"2021-08-26","cited_by_count":149,"area":"rag"},{"id":"2110.10090","title":"Inductive Biases and Variable Creation in Self-Attention Mechanisms","created":"2021-10-19","cited_by_count":144,"area":null},{"id":"2407.07071","title":"Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps","created":"2024-07-09","cited_by_count":142,"area":null},{"id":"2106.01223","title":"A Unified Generative Framework for Various NER Subtasks","created":"2021-06-02","cited_by_count":141,"area":null},{"id":"2305.17560","title":"Scalable Transformer for PDE Surrogate Modeling","created":"2023-05-27","cited_by_count":128,"area":null},{"id":"2104.07788","title":"PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models","created":"2021-04-15","cited_by_count":118,"area":null},{"id":"2103.10206","title":"DanceFormer: Music Conditioned 3D Dance Generation with Parametric Motion Transformer","created":"2021-03-18","cited_by_count":111,"area":null},{"id":"2307.14768","title":"Gloss-free Sign Language Translation: Improving from Visual-Language Pretraining","created":"2023-07-27","cited_by_count":105,"area":null},{"id":"2105.13381","title":"Recent advances and clinical applications of deep learning in medical image analysis","created":"2021-05-27","cited_by_count":104,"area":null},{"id":"2204.04879","title":"How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision","created":"2022-04-11","cited_by_count":102,"area":null},{"id":"2107.07905","title":"Unsupervised Discovery of Object Radiance Fields","created":"2021-07-16","cited_by_count":101,"area":null},{"id":"2406.16008","title":"Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilization","created":"2024-06-23","cited_by_count":101,"area":null},{"id":"1909.01871","title":"Help, Anna! Visual Navigation with Natural Multimodal Assistance via Retrospective Curiosity-Encouraging Imitation Learning","created":"2019-09-04","cited_by_count":100,"area":"offlinerl"},{"id":"2301.13816","title":"Execution-based Code Generation using Deep Reinforcement Learning","created":"2023-01-31","cited_by_count":99,"area":null},{"id":"2106.04300","title":"A Unified Generative Framework for Aspect-Based Sentiment Analysis","created":"2021-06-08","cited_by_count":97,"area":null},{"id":"2108.09661","title":"From Two to One: A New Scene Text Recognizer with Visual Language Modeling Network","created":"2021-08-22","cited_by_count":97,"area":"mllm"},{"id":"2106.02795","title":"Learnable Fourier Features for Multi-Dimensional Spatial Positional Encoding","created":"2021-06-05","cited_by_count":93,"area":null},{"id":"2204.06618","title":"Formal Language Recognition by Hard Attention Transformers: Perspectives from Circuit Complexity","created":"2022-04-13","cited_by_count":93,"area":null},{"id":"2109.09115","title":"Do Long-Range Language Models Actually Use Long-Range Context?","created":"2021-09-19","cited_by_count":92,"area":null},{"id":"2106.09248","title":"X-FACT: A New Benchmark Dataset for Multilingual Fact Checking","created":"2021-06-17","cited_by_count":91,"area":null},{"id":"2205.13328","title":"How Powerful are K-hop Message Passing Graph Neural Networks","created":"2022-05-26","cited_by_count":90,"area":null},{"id":"2006.05405","title":"Retrieval-Augmented Generation for Code Summarization via Hybrid GNN","created":"2020-06-09","cited_by_count":89,"area":"rag"},{"id":"2301.06262","title":"Collaborative Perception in Autonomous Driving: Methods, Datasets and Challenges","created":"2023-01-16","cited_by_count":87,"area":null},{"id":"2211.08545","title":"MapQA: A Dataset for Question Answering on Choropleth Maps","created":"2022-11-15","cited_by_count":85,"area":null},{"id":"2303.11717","title":"A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?","created":"2023-03-21","cited_by_count":84,"area":null},{"id":"1812.04155","title":"Vision-based Navigation with Language-based Assistance via Imitation Learning with Indirect Intervention","created":"2018-12-10","cited_by_count":77,"area":"offlinerl"},{"id":"2109.04553","title":"Is Attention Better Than Matrix Decomposition?","created":"2021-09-09","cited_by_count":77,"area":null},{"id":"2110.11624","title":"SciCap: Generating Captions for Scientific Figures","created":"2021-10-22","cited_by_count":77,"area":null},{"id":"2404.00925","title":"LLMs are Good Sign Language Translators","created":"2024-04-01","cited_by_count":77,"area":null},{"id":"2306.00946","title":"Exposing Attention Glitches with Flip-Flop Language Modeling","created":"2023-06-01","cited_by_count":75,"area":null},{"id":"2009.07253","title":"Autoregressive Knowledge Distillation through Imitation Learning","created":"2020-09-15","cited_by_count":74,"area":"offlinerl"},{"id":"1707.07402","title":"Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback","created":"2017-07-24","cited_by_count":72,"area":"alignment"},{"id":"2205.03983","title":"Building Machine Translation Systems for the Next Thousand Languages","created":"2022-05-09","cited_by_count":69,"area":null},{"id":"2105.07944","title":"TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learning","created":"2021-05-17","cited_by_count":68,"area":null},{"id":"2302.02515","title":"Deep Learning for Time Series Classification and Extrinsic Regression: A Current Survey","created":"2023-02-06","cited_by_count":68,"area":null},{"id":"2212.05136","title":"CLIP-TSA: CLIP-Assisted Temporal Self-Attention for Weakly-Supervised Video Anomaly Detection","created":"2022-12-09","cited_by_count":67,"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":"2304.07438","title":"Tractable Control for Autoregressive Language Generation","created":"2023-04-15","cited_by_count":65,"area":null},{"id":"2203.14263","title":"A General Survey on Attention Mechanisms in Deep Learning","created":"2022-03-27","cited_by_count":64,"area":null},{"id":"2204.09269","title":"A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyond","created":"2022-04-20","cited_by_count":64,"area":null},{"id":"2108.04556","title":"SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation","created":"2021-08-10","cited_by_count":63,"area":null},{"id":"2202.13330","title":"DialFRED: Dialogue-Enabled Agents for Embodied Instruction Following","created":"2022-02-27","cited_by_count":63,"area":null},{"id":"2106.04252","title":"Meta-Learning to Compositionally Generalize","created":"2021-06-08","cited_by_count":62,"area":null},{"id":"2206.08948","title":"CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation","created":"2022-06-17","cited_by_count":60,"area":null},{"id":"2103.11878","title":"BlonDe: An Automatic Evaluation Metric for Document-level Machine Translation","created":"2021-03-22","cited_by_count":58,"area":null},{"id":"2205.14140","title":"CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior","created":"2022-05-27","cited_by_count":55,"area":null},{"id":"2209.15565","title":"Augmenting Operations Research with Auto-Formulation of Optimization Models from Problem Descriptions","created":"2022-09-30","cited_by_count":54,"area":null},{"id":"2312.16475","title":"Federated Continual Learning via Knowledge Fusion: A Survey","created":"2023-12-27","cited_by_count":53,"area":null},{"id":"2402.10350","title":"Large Language Models for Forecasting and Anomaly Detection: A Systematic Literature Review","created":"2024-02-15","cited_by_count":53,"area":null},{"id":"2101.09983","title":"Adversarial Text-to-Image Synthesis: A Review","created":"2021-01-25","cited_by_count":52,"area":null},{"id":"2208.13629","title":"A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directions","created":"2022-08-29","cited_by_count":52,"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":"2302.04973","title":"Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames","created":"2023-02-09","cited_by_count":51,"area":null},{"id":"2307.07361","title":"Gloss Attention for Gloss-free Sign Language Translation","created":"2023-07-14","cited_by_count":51,"area":null},{"id":"2202.01338","title":"Regression Transformer: Concurrent sequence regression and generation for molecular language modeling","created":"2022-02-01","cited_by_count":50,"area":null},{"id":"2202.06689","title":"CodeFill: Multi-token Code Completion by Jointly Learning from Structure and Naming Sequences","created":"2022-02-14","cited_by_count":50,"area":null},{"id":"2104.05485","title":"Predicting Pedestrian Crossing Intention with Feature Fusion and Spatio-Temporal Attention","created":"2021-04-12","cited_by_count":48,"area":null},{"id":"2107.13509","title":"The Who in XAI: How AI Background Shapes Perceptions of AI Explanations","created":"2021-07-28","cited_by_count":48,"area":null},{"id":"2107.11906","title":"H-Transformer-1D: Fast One-Dimensional Hierarchical Attention for Sequences","created":"2021-07-25","cited_by_count":47,"area":null},{"id":"2203.05132","title":"Compilable Neural Code Generation with Compiler Feedback","created":"2022-03-10","cited_by_count":47,"area":null},{"id":"2204.08128","title":"Less is More: Learning to Refine Dialogue History for Personalized Dialogue Generation","created":"2022-04-18","cited_by_count":47,"area":null},{"id":"2101.06223","title":"LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning","created":"2021-01-15","cited_by_count":46,"area":null},{"id":"2202.05798","title":"The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns via Spotlights of Attention","created":"2022-02-11","cited_by_count":46,"area":null},{"id":"2101.10504","title":"On the Evaluation of Vision-and-Language Navigation Instructions","created":"2021-01-26","cited_by_count":45,"area":null},{"id":"2203.02225","title":"ClarET: Pre-training a Correlation-Aware Context-To-Event Transformer for Event-Centric Generation and Classification","created":"2022-03-04","cited_by_count":45,"area":null},{"id":"2305.16642","title":"Improving Position Encoding of Transformers for Multivariate Time Series Classification","created":"2023-05-26","cited_by_count":45,"area":null},{"id":"2103.12279","title":"SelfExplain: A Self-Explaining Architecture for Neural Text Classifiers","created":"2021-03-23","cited_by_count":44,"area":null},{"id":"2203.10316","title":"Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction","created":"2022-03-19","cited_by_count":44,"area":"lr"},{"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":"2201.12114","title":"Rethinking Attention-Model Explainability through Faithfulness Violation Test","created":"2022-01-28","cited_by_count":43,"area":null},{"id":"2107.05214","title":"Split, embed and merge: An accurate table structure recognizer","created":"2021-07-12","cited_by_count":42,"area":null},{"id":"2102.02810","title":"Controlling Hallucinations at Word Level in Data-to-Text Generation","created":"2021-02-04","cited_by_count":41,"area":null},{"id":"2103.08849","title":"Multilingual Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer of Vision-Language Models","created":"2021-03-16","cited_by_count":41,"area":"mllm"},{"id":"2104.07012","title":"Sparse Attention with Linear Units","created":"2021-04-14","cited_by_count":41,"area":null},{"id":"2205.14219","title":"Controllable Text Generation with Neurally-Decomposed Oracle","created":"2022-05-27","cited_by_count":41,"area":null},{"id":"2105.14039","title":"Towards mental time travel: a hierarchical memory for reinforcement learning agents","created":"2021-05-28","cited_by_count":40,"area":null},{"id":"2103.04886","title":"Lipschitz Normalization for Self-Attention Layers with Application to Graph Neural Networks","created":"2021-03-08","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":"2103.07601","title":"Approximating How Single Head Attention Learns","created":"2021-03-13","cited_by_count":38,"area":null},{"id":"2105.14528","title":"Fast Nearest Neighbor Machine Translation","created":"2021-05-30","cited_by_count":37,"area":null}],"next_cursor":"100"}