{"total":215,"rows":[{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703,"area":null},{"id":"2108.12409","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","created":"2021-08-27","cited_by_count":1103,"area":null},{"id":"2102.11174","title":"Linear Transformers Are Secretly Fast Weight Programmers","created":"2021-02-22","cited_by_count":502,"area":null},{"id":"2103.03404","title":"Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth","created":"2021-03-05","cited_by_count":419,"area":null},{"id":"2111.09525","title":"SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization","created":"2021-11-18","cited_by_count":407,"area":null},{"id":"2103.12731","title":"Scaling Local Self-Attention for Parameter Efficient Visual Backbones","created":"2021-03-23","cited_by_count":220,"area":null},{"id":"2106.05667","title":"GraphiT: Encoding Graph Structure in Transformers","created":"2021-06-10","cited_by_count":147,"area":null},{"id":"2105.04387","title":"Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey","created":"2021-05-10","cited_by_count":130,"area":null},{"id":"2107.03158","title":"A Survey on Data Augmentation for Text Classification","created":"2021-07-07","cited_by_count":111,"area":null},{"id":"2104.07652","title":"Geometry-Free View Synthesis: Transformers and no 3D Priors","created":"2021-04-15","cited_by_count":100,"area":null},{"id":"2210.14793","title":"M$^3$ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design","created":"2022-10-26","cited_by_count":98,"area":"moe"},{"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":"2303.16406","title":"Hierarchical Video-Moment Retrieval and Step-Captioning","created":"2023-03-29","cited_by_count":83,"area":null},{"id":"2109.04553","title":"Is Attention Better Than Matrix Decomposition?","created":"2021-09-09","cited_by_count":77,"area":null},{"id":"2106.09449","title":"DocNLI: A Large-scale Dataset for Document-level Natural Language Inference","created":"2021-06-17","cited_by_count":75,"area":null},{"id":"2308.16898","title":"Transformers as Support Vector Machines","created":"2023-08-31","cited_by_count":74,"area":null},{"id":"2106.16138","title":"XLM-E: Cross-lingual Language Model Pre-training via ELECTRA","created":"2021-06-30","cited_by_count":72,"area":null},{"id":"2107.13541","title":"Towards Robustness Against Natural Language Word Substitutions","created":"2021-07-28","cited_by_count":69,"area":null},{"id":"2312.04916","title":"EE-LLM: Large-Scale Training and Inference of Early-Exit Large Language Models with 3D Parallelism","created":"2023-12-08","cited_by_count":69,"area":"inference"},{"id":"2102.08597","title":"Beyond Fully-Connected Layers with Quaternions: Parameterization of Hypercomplex Multiplications with $1/n$ Parameters","created":"2021-02-17","cited_by_count":66,"area":null},{"id":"2201.05991","title":"Video Transformers: A Survey","created":"2022-01-16","cited_by_count":63,"area":null},{"id":"2211.10960","title":"CoCoNet: Coupled Contrastive Learning Network with Multi-level Feature Ensemble for Multi-modality Image Fusion","created":"2022-11-20","cited_by_count":63,"area":null},{"id":"2108.09084","title":"Fastformer: Additive Attention Can Be All You Need","created":"2021-08-20","cited_by_count":61,"area":null},{"id":"2105.04371","title":"Poolingformer: Long Document Modeling with Pooling Attention","created":"2021-05-10","cited_by_count":60,"area":null},{"id":"2306.13596","title":"Max-Margin Token Selection in Attention Mechanism","created":"2023-06-23","cited_by_count":58,"area":null},{"id":"2201.03230","title":"Swin Transformer for Fast MRI","created":"2022-01-10","cited_by_count":56,"area":null},{"id":"2406.10729","title":"A Comprehensive Survey of Foundation Models in Medicine","created":"2024-06-15","cited_by_count":56,"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":"2404.15956","title":"A Survey on Visual Mamba","created":"2024-04-24","cited_by_count":50,"area":"ssm"},{"id":"2205.08303","title":"MulT: An End-to-End Multitask Learning Transformer","created":"2022-05-17","cited_by_count":48,"area":null},{"id":"2211.08110","title":"HeatViT: Hardware-Efficient Adaptive Token Pruning for Vision Transformers","created":"2022-11-15","cited_by_count":46,"area":"inference"},{"id":"2202.09381","title":"Synthetic Disinformation Attacks on Automated Fact Verification Systems","created":"2022-02-18","cited_by_count":44,"area":null},{"id":"2110.04722","title":"Transformer-based Dual Relation Graph for Multi-label Image Recognition","created":"2021-10-10","cited_by_count":41,"area":null},{"id":"2307.11353","title":"What can a Single Attention Layer Learn? A Study Through the Random Features Lens","created":"2023-07-21","cited_by_count":40,"area":null},{"id":"2101.08001","title":"UPDeT: Universal Multi-agent Reinforcement Learning via Policy Decoupling with Transformers","created":"2021-01-20","cited_by_count":39,"area":null},{"id":"2204.07756","title":"Visual Attention Methods in Deep Learning: An In-Depth Survey","created":"2022-04-16","cited_by_count":37,"area":null},{"id":"2310.12680","title":"On the Optimization and Generalization of Multi-head Attention","created":"2023-10-19","cited_by_count":37,"area":null},{"id":"2108.01316","title":"RAIN: Reinforced Hybrid Attention Inference Network for Motion Forecasting","created":"2021-08-03","cited_by_count":36,"area":null},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36,"area":null},{"id":"2401.07872","title":"The What, Why, and How of Context Length Extension Techniques in Large Language Models -- A Detailed Survey","created":"2024-01-15","cited_by_count":33,"area":null},{"id":"2203.10995","title":"Word Order Does Matter (And Shuffled Language Models Know It)","created":"2022-03-21","cited_by_count":32,"area":null},{"id":"2312.00751","title":"Mitigating Over-smoothing in Transformers via Regularized Nonlocal Functionals","created":"2023-12-01","cited_by_count":32,"area":null},{"id":"2104.08676","title":"Distributed NLI: Learning to Predict Human Opinion Distributions for Language Reasoning","created":"2021-04-18","cited_by_count":31,"area":null},{"id":"2105.06458","title":"High-Resolution Complex Scene Synthesis with Transformers","created":"2021-05-13","cited_by_count":31,"area":null},{"id":"2210.10040","title":"The Tail Wagging the Dog: Dataset Construction Biases of Social Bias Benchmarks","created":"2022-10-18","cited_by_count":31,"area":null},{"id":"2305.14623","title":"Self-Checker: Plug-and-Play Modules for Fact-Checking with Large Language Models","created":"2023-05-24","cited_by_count":31,"area":null},{"id":"2110.08678","title":"Improving Transformers with Probabilistic Attention Keys","created":"2021-10-16","cited_by_count":28,"area":null},{"id":"2304.11431","title":"A Review of Deep Learning for Video Captioning","created":"2023-04-22","cited_by_count":28,"area":null},{"id":"2110.06206","title":"StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learning","created":"2021-10-12","cited_by_count":27,"area":null},{"id":"2306.09719","title":"Pushing the Limits of ChatGPT on NLP Tasks","created":"2023-06-16","cited_by_count":27,"area":null},{"id":"2310.10837","title":"Approximating Two-Layer Feedforward Networks for Efficient Transformers","created":"2023-10-16","cited_by_count":27,"area":null},{"id":"2312.04782","title":"Make Them Spill the Beans! Coercive Knowledge Extraction from (Production) LLMs","created":"2023-12-08","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":"2105.14167","title":"NeuralLog: Natural Language Inference with Joint Neural and Logical Reasoning","created":"2021-05-29","cited_by_count":25,"area":null},{"id":"2106.05251","title":"Bayesian Attention Belief Networks","created":"2021-06-09","cited_by_count":25,"area":null},{"id":"2103.09013","title":"Dense Interaction Learning for Video-based Person Re-identification","created":"2021-03-16","cited_by_count":24,"area":null},{"id":"2103.01075","title":"OmniNet: Omnidirectional Representations from Transformers","created":"2021-03-01","cited_by_count":23,"area":null},{"id":"2102.04754","title":"Bayesian Transformer Language Models for Speech Recognition","created":"2021-02-09","cited_by_count":22,"area":null},{"id":"2102.10934","title":"Using Prior Knowledge to Guide BERT's Attention in Semantic Textual Matching Tasks","created":"2021-02-22","cited_by_count":22,"area":null},{"id":"1708.02300","title":"Reinforced Video Captioning with Entailment Rewards","created":"2017-08-07","cited_by_count":21,"area":"alignment"},{"id":"2212.01231","title":"BEV-SAN: Accurate BEV 3D Object Detection via Slice Attention Networks","created":"2022-12-02","cited_by_count":20,"area":null},{"id":"2108.04603","title":"Relation-aware Compositional Zero-shot Learning for Attribute-Object Pair Recognition","created":"2021-08-10","cited_by_count":19,"area":null},{"id":"2210.04710","title":"Empowering the Fact-checkers! Automatic Identification of Claim Spans on Twitter","created":"2022-10-10","cited_by_count":19,"area":null},{"id":"2105.02274","title":"Rethinking Search: Making Domain Experts out of Dilettantes","created":"2021-05-05","cited_by_count":18,"area":null},{"id":"2111.08543","title":"WikiContradiction: Detecting Self-Contradiction Articles on Wikipedia","created":"2021-11-16","cited_by_count":17,"area":null},{"id":"2202.06167","title":"Ultra-fine Entity Typing with Indirect Supervision from Natural Language Inference","created":"2022-02-12","cited_by_count":17,"area":null},{"id":"2106.01191","title":"Topic-Aware Evidence Reasoning and Stance-Aware Aggregation for Fact Verification","created":"2021-06-02","cited_by_count":16,"area":null},{"id":"2109.04775","title":"A Strong Baseline for Query Efficient Attacks in a Black Box Setting","created":"2021-09-10","cited_by_count":16,"area":null},{"id":"2310.11685","title":"Why Softmax Attention Outperforms Linear Attention","created":"2023-10-18","cited_by_count":15,"area":null},{"id":"2401.15347","title":"A Comprehensive Survey of Compression Algorithms for Language Models","created":"2024-01-27","cited_by_count":15,"area":null},{"id":"2110.12567","title":"Alignment Attention by Matching Key and Query Distributions","created":"2021-10-25","cited_by_count":14,"area":null},{"id":"2212.06933","title":"Paraphrase Identification with Deep Learning: A Review of Datasets and Methods","created":"2022-12-13","cited_by_count":13,"area":null},{"id":"2104.04488","title":"Explaining Neural Network Predictions on Sentence Pairs via Learning Word-Group Masks","created":"2021-04-09","cited_by_count":12,"area":null},{"id":"2105.07623","title":"Sentence Similarity Based on Contexts","created":"2021-05-17","cited_by_count":12,"area":null},{"id":"2112.13310","title":"Miti-DETR: Object Detection based on Transformers with Mitigatory Self-Attention Convergence","created":"2021-12-26","cited_by_count":12,"area":null},{"id":"2206.04928","title":"GAMR: A Guided Attention Model for (visual) Reasoning","created":"2022-06-10","cited_by_count":12,"area":"lr"},{"id":"2209.03755","title":"Fact-Saboteurs: A Taxonomy of Evidence Manipulation Attacks against Fact-Verification Systems","created":"2022-09-07","cited_by_count":12,"area":null},{"id":"2204.02007","title":"Fact Checking with Insufficient Evidence","created":"2022-04-05","cited_by_count":11,"area":null},{"id":"2402.15989","title":"PIDformer: Transformer Meets Control Theory","created":"2024-02-25","cited_by_count":11,"area":null},{"id":"2406.01895","title":"Explicitly Encoding Structural Symmetry is Key to Length Generalization in Arithmetic Tasks","created":"2024-06-04","cited_by_count":11,"area":"lr"},{"id":"2109.08927","title":"Weakly Supervised Explainable Phrasal Reasoning with Neural Fuzzy Logic","created":"2021-09-18","cited_by_count":10,"area":null},{"id":"2112.11540","title":"Mixed Precision of Quantization of Transformer Language Models for Speech Recognition","created":"2021-11-29","cited_by_count":10,"area":null},{"id":"2403.19113","title":"FACTOID: FACtual enTailment fOr hallucInation Detection","created":"2024-03-28","cited_by_count":10,"area":null},{"id":"2502.20525","title":"Revisiting Kernel Attention with Correlated Gaussian Process Representation","created":"2025-02-27","cited_by_count":10,"area":null},{"id":"2104.08712","title":"PaCo: Preconditions Attributed to Commonsense Knowledge","created":"2021-04-18","cited_by_count":9,"area":null},{"id":"2112.04075","title":"Active Sensing for Communications by Learning","created":"2021-12-08","cited_by_count":9,"area":null},{"id":"2203.02898","title":"Divide and Conquer: Text Semantic Matching with Disentangled Keywords and Intents","created":"2022-03-06","cited_by_count":9,"area":null},{"id":"2204.09244","title":"DAME: Domain Adaptation for Matching Entities","created":"2022-04-20","cited_by_count":9,"area":null},{"id":"2204.13921","title":"QRelScore: Better Evaluating Generated Questions with Deeper Understanding of Context-aware Relevance","created":"2022-04-29","cited_by_count":9,"area":null},{"id":"2208.06643","title":"Recent Progress in Transformer-based Medical Image Analysis","created":"2022-08-13","cited_by_count":9,"area":null},{"id":"2301.05334","title":"TransfQMix: Transformers for Leveraging the Graph Structure of Multi-Agent Reinforcement Learning Problems","created":"2023-01-13","cited_by_count":9,"area":null},{"id":"2405.15926","title":"Dissecting the Interplay of Attention Paths in a Statistical Mechanics Theory of Transformers","created":"2024-05-24","cited_by_count":9,"area":null},{"id":"2104.08763","title":"Making Attention Mechanisms More Robust and Interpretable with Virtual Adversarial Training","created":"2021-04-18","cited_by_count":8,"area":null},{"id":"2105.14115","title":"Towards More Equitable Question Answering Systems: How Much More Data Do You Need?","created":"2021-05-28","cited_by_count":8,"area":null},{"id":"2508.08435","title":"Fast weight programming and linear transformers: from machine learning to neurobiology","created":"2025-08-11","cited_by_count":8,"area":null},{"id":"1812.01483","title":"CompILE: Compositional Imitation Learning and Execution","created":"2018-12-04","cited_by_count":7,"area":"offlinerl"},{"id":"2110.08018","title":"Structural Characterization for Dialogue Disentanglement","created":"2021-10-15","cited_by_count":7,"area":null},{"id":"2206.14337","title":"Deformable Graph Transformer","created":"2022-06-29","cited_by_count":7,"area":null},{"id":"2405.03419","title":"Automated Metaheuristic Algorithm Design with Autoregressive Learning","created":"2024-05-06","cited_by_count":7,"area":null},{"id":"2406.13762","title":"Unveiling the Hidden Structure of Self-Attention via Kernel Principal Component Analysis","created":"2024-06-19","cited_by_count":7,"area":null}],"next_cursor":"100"}