{"total":53,"rows":[{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703,"area":null},{"id":"2102.10882","title":"Conditional Positional Encodings for Vision Transformers","created":"2021-02-22","cited_by_count":406,"area":null},{"id":"2106.04554","title":"A Survey of Transformers","created":"2021-06-08","cited_by_count":401,"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":"2105.11115","title":"Self-Attention Networks Can Process Bounded Hierarchical Languages","created":"2021-05-24","cited_by_count":105,"area":null},{"id":"2102.11090","title":"Position Information in Transformers: An Overview","created":"2021-02-22","cited_by_count":103,"area":null},{"id":"2106.02795","title":"Learnable Fourier Features for Multi-Dimensional Spatial Positional Encoding","created":"2021-06-05","cited_by_count":93,"area":null},{"id":"2110.05006","title":"Pre-trained Language Models in Biomedical Domain: A Systematic Survey","created":"2021-10-11","cited_by_count":87,"area":null},{"id":"2205.13401","title":"Your Transformer May Not be as Powerful as You Expect","created":"2022-05-26","cited_by_count":55,"area":null},{"id":"2106.03143","title":"CAPE: Encoding Relative Positions with Continuous Augmented Positional Embeddings","created":"2021-06-06","cited_by_count":47,"area":null},{"id":"2412.17739","title":"Fourier Position Embedding: Enhancing Attention's Periodic Extension for Length Generalization","created":"2024-12-23","cited_by_count":39,"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":"2107.02561","title":"Rethinking Positional Encoding","created":"2021-07-06","cited_by_count":37,"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":"2102.09269","title":"Dynamic Memory based Attention Network for Sequential Recommendation","created":"2021-02-18","cited_by_count":16,"area":null},{"id":"2205.08987","title":"Trading Positional Complexity vs. Deepness in Coordinate Networks","created":"2022-05-18","cited_by_count":16,"area":null},{"id":"2306.09827","title":"Building Blocks for a Complex-Valued Transformer Architecture","created":"2023-06-16","cited_by_count":16,"area":null},{"id":"2406.09897","title":"3D-RPE: Enhancing Long-Context Modeling Through 3D Rotary Position Encoding","created":"2024-06-14","cited_by_count":13,"area":null},{"id":"2405.06784","title":"Open Challenges and Opportunities in Federated Foundation Models Towards Biomedical Healthcare","created":"2024-05-10","cited_by_count":12,"area":null},{"id":"2105.00412","title":"TE-ESN: Time Encoding Echo State Network for Prediction Based on Irregularly Sampled Time Series Data","created":"2021-05-02","cited_by_count":10,"area":null},{"id":"2312.16045","title":"Algebraic Positional Encodings","created":"2023-12-26","cited_by_count":10,"area":null},{"id":"2509.10534","title":"Decoupling the \"What\" and \"Where\" With Polar Coordinate Positional Embeddings","created":"2025-09-05","cited_by_count":10,"area":null},{"id":"2305.20019","title":"Monotonic Location Attention for Length Generalization","created":"2023-05-31","cited_by_count":9,"area":null},{"id":"2503.00533","title":"BodyGen: Advancing Towards Efficient Embodiment Co-Design","created":"2025-03-01","cited_by_count":9,"area":null},{"id":"2112.11577","title":"Learning Positional Embeddings for Coordinate-MLPs","created":"2021-12-21","cited_by_count":7,"area":null},{"id":"2512.07805","title":"Group Representational Position Encoding","created":"2025-12-08","cited_by_count":5,"area":null},{"id":"2409.12175","title":"Expanding Expressivity in Transformer Models with M\\\"obiusAttention","created":"2024-09-08","cited_by_count":4,"area":null},{"id":"2107.05907","title":"Conformer-based End-to-end Speech Recognition With Rotary Position Embedding","created":"2021-07-13","cited_by_count":3,"area":null},{"id":"2109.02580","title":"Ultra-high Resolution Image Segmentation via Locality-aware Context Fusion and Alternating Local Enhancement","created":"2021-09-06","cited_by_count":3,"area":null},{"id":"2302.13812","title":"Adapting Pre-trained Language Models for Quantum Natural Language Processing","created":"2023-02-24","cited_by_count":2,"area":null},{"id":"2405.13046","title":"LeaPformer: Enabling Linear Transformers for Autoregressive and Simultaneous Tasks via Learned Proportions","created":"2024-05-18","cited_by_count":2,"area":null},{"id":"2410.19760","title":"Movie Trailer Genre Classification Using Multimodal Pretrained Features","created":"2024-10-11","cited_by_count":2,"area":null},{"id":"2502.10154","title":"Video Soundtrack Generation by Aligning Emotions and Temporal Boundaries","created":"2025-02-14","cited_by_count":2,"area":null},{"id":"2505.21465","title":"ID-Align: RoPE-Conscious Position Remapping for Dynamic High-Resolution Adaptation in Vision-Language Models","created":"2025-05-27","cited_by_count":2,"area":"mllm"},{"id":"2506.13277","title":"SeqPE: Transformer with Sequential Position Encoding","created":"2025-06-16","cited_by_count":2,"area":null},{"id":"2202.11364","title":"FastRPB: a Scalable Relative Positional Encoding for Long Sequence Tasks","created":"2022-02-23","cited_by_count":1,"area":null},{"id":"2204.08688","title":"DecBERT: Enhancing the Language Understanding of BERT with Causal Attention Masks","created":"2022-04-19","cited_by_count":1,"area":null},{"id":"2209.05929","title":"Document-aware Positional Encoding and Linguistic-guided Encoding for Abstractive Multi-document Summarization","created":"2022-09-13","cited_by_count":1,"area":null},{"id":"2310.12864","title":"The Locality and Symmetry of Positional Encodings","created":"2023-10-19","cited_by_count":1,"area":null},{"id":"2402.13208","title":"How do Hyenas deal with Human Speech? Speech Recognition and Translation with ConfHyena","created":"2024-02-20","cited_by_count":1,"area":null},{"id":"2409.15105","title":"SPformer: A Transformer Based DRL Decision Making Method for Connected Automated Vehicles","created":"2024-09-23","cited_by_count":1,"area":"deeprl"},{"id":"2508.18308","title":"CoPE: A Lightweight Complex Positional Encoding","created":"2025-08-23","cited_by_count":1,"area":null},{"id":"2112.10543","title":"Spiral Language Modeling","created":"2021-12-20","cited_by_count":0,"area":null},{"id":"2301.03953","title":"Channel-aware Decoupling Network for Multi-turn Dialogue Comprehension","created":"2023-01-10","cited_by_count":0,"area":null},{"id":"2307.08586","title":"Syntax-Aware Complex-Valued Neural Machine Translation","created":"2023-07-17","cited_by_count":0,"area":null},{"id":"2406.07049","title":"GridPE: A Grid Cell-Inspired Unified Position Embedding for Arbitrary-Dimensional Spaces","created":"2024-06-11","cited_by_count":0,"area":null},{"id":"2411.00054","title":"eDOC: Explainable Decoding Out-of-domain Cell Types with Evidential Learning","created":"2024-10-30","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":"2502.01706","title":"Comply: Learning Sentences with Complex Weights inspired by Fruit Fly Olfaction","created":"2025-02-03","cited_by_count":0,"area":null},{"id":"2601.02728","title":"CRoPE: Efficient Parametrization of Rotary Positional Embedding","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2603.00432","title":"A Typologically Grounded Evaluation Framework for Word Order and Morphology Sensitivity in Multilingual Masked LMs","created":"2026-02-28","cited_by_count":0,"area":null},{"id":"2603.28205","title":"Beyond Cosine Similarity: Zero-Initialized Residual Complex Projection for Aspect-Based Sentiment Analysis","created":"2026-03-30","cited_by_count":0,"area":null}],"next_cursor":null}