{"total":73,"rows":[{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703,"area":null},{"id":"2107.14222","title":"Rethinking and Improving Relative Position Encoding for Vision Transformer","created":"2021-07-29","cited_by_count":207,"area":null},{"id":"2209.10655","title":"Mega: Moving Average Equipped Gated Attention","created":"2022-09-21","cited_by_count":179,"area":null},{"id":"2206.06565","title":"LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks","created":"2022-06-14","cited_by_count":148,"area":null},{"id":"2102.13019","title":"Investigating the Limitations of Transformers with Simple Arithmetic Tasks","created":"2021-02-25","cited_by_count":139,"area":null},{"id":"2102.11090","title":"Position Information in Transformers: An Overview","created":"2021-02-22","cited_by_count":103,"area":null},{"id":"2205.09921","title":"KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation","created":"2022-05-20","cited_by_count":86,"area":null},{"id":"2207.09814","title":"NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesis","created":"2022-07-20","cited_by_count":71,"area":null},{"id":"2306.15400","title":"Length Generalization in Arithmetic Transformers","created":"2023-06-27","cited_by_count":66,"area":null},{"id":"2410.15926","title":"Mitigating Object Hallucination via Concentric Causal Attention","created":"2024-10-21","cited_by_count":49,"area":"lr"},{"id":"2106.03143","title":"CAPE: Encoding Relative Positions with Continuous Augmented Positional Embeddings","created":"2021-06-06","cited_by_count":47,"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":"2108.12517","title":"SIGN: Spatial-information Incorporated Generative Network for Generalized Zero-shot Semantic Segmentation","created":"2021-08-27","cited_by_count":41,"area":null},{"id":"2403.14852","title":"KeyPoint Relative Position Encoding for Face Recognition","created":"2024-03-21","cited_by_count":38,"area":null},{"id":"2105.08399","title":"Relative Positional Encoding for Transformers with Linear Complexity","created":"2021-05-18","cited_by_count":37,"area":null},{"id":"2109.05644","title":"SHAPE: Shifted Absolute Position Embedding for Transformers","created":"2021-09-13","cited_by_count":37,"area":null},{"id":"2505.16381","title":"PaTH Attention: Position Encoding via Accumulating Householder Transformations","created":"2025-05-22","cited_by_count":34,"area":null},{"id":"2206.01136","title":"Transforming medical imaging with Transformers? A comparative review of key properties, current progresses, and future perspectives","created":"2022-06-02","cited_by_count":33,"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":"2312.17044","title":"Length Extrapolation of Transformers: A Survey from the Perspective of Positional Encoding","created":"2023-12-28","cited_by_count":32,"area":null},{"id":"2110.04655","title":"Disentangled Sequence to Sequence Learning for Compositional Generalization","created":"2021-10-09","cited_by_count":30,"area":null},{"id":"2206.06801","title":"Peripheral Vision Transformer","created":"2022-06-14","cited_by_count":27,"area":null},{"id":"2110.05841","title":"Relative Molecule Self-Attention Transformer","created":"2021-10-12","cited_by_count":21,"area":null},{"id":"2311.05613","title":"Window Attention is Bugged: How not to Interpolate Position Embeddings","created":"2023-11-09","cited_by_count":18,"area":null},{"id":"2307.09270","title":"Linearized Relative Positional Encoding","created":"2023-07-18","cited_by_count":17,"area":null},{"id":"2502.12370","title":"Positional Encoding in Transformer-Based Time Series Models: A Survey","created":"2025-02-17","cited_by_count":14,"area":null},{"id":"2505.04616","title":"Person Recognition at Altitude and Range: Fusion of Face, Body Shape and Gait","created":"2025-05-07","cited_by_count":14,"area":null},{"id":"2107.05223","title":"BERT-like Pre-training for Symbolic Piano Music Classification Tasks","created":"2021-07-12","cited_by_count":12,"area":null},{"id":"2507.09184","title":"MCA-LLaVA: Manhattan Causal Attention for Reducing Hallucination in Large Vision-Language Models","created":"2025-07-12","cited_by_count":12,"area":"mllm"},{"id":"2106.05505","title":"Convolutions and Self-Attention: Re-interpreting Relative Positions in Pre-trained Language Models","created":"2021-06-10","cited_by_count":11,"area":null},{"id":"2304.07920","title":"Causal Decision Transformer for Recommender Systems via Offline Reinforcement Learning","created":"2023-04-17","cited_by_count":11,"area":"offlinerl"},{"id":"2305.00398","title":"SLSG: Industrial Image Anomaly Detection by Learning Better Feature Embeddings and One-Class Classification","created":"2023-04-30","cited_by_count":10,"area":null},{"id":"2104.07704","title":"Syntax-Aware Graph-to-Graph Transformer for Semantic Role Labelling","created":"2021-04-15","cited_by_count":8,"area":null},{"id":"2502.16792","title":"The Role of Sparsity for Length Generalization in Transformers","created":"2025-02-24","cited_by_count":8,"area":null},{"id":"2109.05388","title":"The Impact of Positional Encodings on Multilingual Compression","created":"2021-09-11","cited_by_count":5,"area":null},{"id":"2212.05830","title":"P-Transformer: Towards Better Document-to-Document Neural Machine Translation","created":"2022-12-12","cited_by_count":5,"area":null},{"id":"2310.17936","title":"Transformers as Graph-to-Graph Models","created":"2023-10-27","cited_by_count":5,"area":null},{"id":"2308.01904","title":"DETR Doesn't Need Multi-Scale or Locality Design","created":"2023-08-03","cited_by_count":4,"area":null},{"id":"2404.04530","title":"A Morphology-Based Investigation of Positional Encodings","created":"2024-04-06","cited_by_count":4,"area":null},{"id":"2212.05982","title":"Real-World Compositional Generalization with Disentangled Sequence-to-Sequence Learning","created":"2022-12-12","cited_by_count":3,"area":null},{"id":"2309.02326","title":"Revisiting File Context for Source Code Summarization","created":"2023-09-05","cited_by_count":3,"area":null},{"id":"2311.12885","title":"Long-MIL: Scaling Long Contextual Multiple Instance Learning for Histopathology Whole Slide Image Analysis","created":"2023-11-21","cited_by_count":3,"area":null},{"id":"2403.17729","title":"EulerFormer: Sequential User Behavior Modeling with Complex Vector Attention","created":"2024-03-26","cited_by_count":3,"area":null},{"id":"2606.04032","title":"Do Transformers Need Three Projections? Systematic Study of QKV Variants","created":"2026-06-01","cited_by_count":3,"area":null},{"id":"2310.19676","title":"HyPE: Attention with Hyperbolic Biases for Relative Positional Encoding","created":"2023-10-30","cited_by_count":2,"area":null},{"id":"2407.19294","title":"Rethinking Attention Module Design for Point Cloud Analysis","created":"2024-07-27","cited_by_count":2,"area":null},{"id":"2506.13277","title":"SeqPE: Transformer with Sequential Position Encoding","created":"2025-06-16","cited_by_count":2,"area":null},{"id":"2103.05497","title":"Symbolic integration by integrating learning models with different strengths and weaknesses","created":"2021-03-09","cited_by_count":1,"area":null},{"id":"2201.10936","title":"FIGARO: Generating Symbolic Music with Fine-Grained Artistic Control","created":"2022-01-26","cited_by_count":1,"area":null},{"id":"2204.04504","title":"TANet: Thread-Aware Pretraining for Abstractive Conversational Summarization","created":"2022-04-09","cited_by_count":1,"area":null},{"id":"2207.07284","title":"Parameterization of Cross-Token Relations with Relative Positional Encoding for Vision MLP","created":"2022-07-15","cited_by_count":1,"area":null},{"id":"2302.06683","title":"Enhancing Multivariate Time Series Classifiers through Self-Attention and Relative Positioning Infusion","created":"2023-02-13","cited_by_count":1,"area":null},{"id":"2304.13567","title":"Technical Report: Impact of Position Bias on Language Models in Token Classification","created":"2023-04-26","cited_by_count":1,"area":null},{"id":"2305.10552","title":"Deep Multiple Instance Learning with Distance-Aware Self-Attention","created":"2023-05-17","cited_by_count":1,"area":null},{"id":"2312.15815","title":"Compositional Generalization in Spoken Language Understanding","created":"2023-12-25","cited_by_count":1,"area":null},{"id":"2401.09627","title":"SymTC: A Symbiotic Transformer-CNN Net for Instance Segmentation of Lumbar Spine MRI","created":"2024-01-17","cited_by_count":1,"area":null},{"id":"2405.03904","title":"Transformer models as an efficient replacement for statistical test suites to evaluate the quality of random numbers","created":"2024-05-06","cited_by_count":1,"area":null},{"id":"2408.10264","title":"Order-Preserving Dimension Reduction for Multimodal Semantic Embedding","created":"2024-08-15","cited_by_count":1,"area":null},{"id":"2501.13428","title":"Softplus Attention with Re-weighting Boosts Length Extrapolation in Large Language Models","created":"2025-01-23","cited_by_count":1,"area":null},{"id":"2503.04174","title":"UniNet: A Unified Multi-granular Traffic Modeling Framework for Network Security","created":"2025-03-06","cited_by_count":1,"area":null},{"id":"2503.04355","title":"Layer-Specific Scaling of Positional Encodings for Superior Long-Context Modeling","created":"2025-03-06","cited_by_count":1,"area":null},{"id":"2509.12635","title":"Positional Encoding via Token-Aware Phase Attention","created":"2025-09-16","cited_by_count":1,"area":null},{"id":"2511.08139","title":"On the Interplay between Positional Encodings, Morphological Complexity, and Word Order Flexibility","created":"2025-11-11","cited_by_count":1,"area":null},{"id":"2109.12788","title":"Multiplicative Position-aware Transformer Models for Language Understanding","created":"2021-09-27","cited_by_count":0,"area":null},{"id":"2205.07177","title":"Hero-Gang Neural Model For Named Entity Recognition","created":"2022-05-15","cited_by_count":0,"area":null},{"id":"2206.09111","title":"VReBERT: A Simple and Flexible Transformer for Visual Relationship Detection","created":"2022-06-18","cited_by_count":0,"area":null},{"id":"2401.17588","title":"Local and Global Contexts for Conversation","created":"2024-01-31","cited_by_count":0,"area":null},{"id":"2409.03767","title":"EMCNet : Graph-Nets for Electron Micrographs Classification","created":"2024-08-21","cited_by_count":0,"area":null},{"id":"2412.11459","title":"Rethinking Associative Memory Mechanism in Induction Head","created":"2024-12-16","cited_by_count":0,"area":"lr"},{"id":"2508.02425","title":"Multi-Class Human/Object Detection on Robot Manipulators using Proprioceptive Sensing","created":"2025-08-04","cited_by_count":0,"area":null},{"id":"2509.16629","title":"Causality-Induced Positional Encoding for Transformer-Based Representation Learning of Non-Sequential Features","created":"2025-09-20","cited_by_count":0,"area":null},{"id":"2601.00698","title":"BSAT: B-Spline Adaptive Tokenizer for Long-Term Time Series Forecasting","created":"2026-01-02","cited_by_count":0,"area":null},{"id":"2609.15013","title":"Overflip: Repetition-Induced Label Flips in Guardrail Models","created":"2026-09-14","cited_by_count":0,"area":"safety"}],"next_cursor":null}