{"total":58,"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":"2305.16843","title":"Randomized Positional Encodings Boost Length Generalization of Transformers","created":"2023-05-26","cited_by_count":117,"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":"2112.04035","title":"Relating transformers to models and neural representations of the hippocampal formation","created":"2021-12-07","cited_by_count":62,"area":null},{"id":"2104.09125","title":"SAPE: Spatially-Adaptive Progressive Encoding for Neural Optimization","created":"2021-04-19","cited_by_count":59,"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":"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":"2405.14722","title":"DAPE: Data-Adaptive Positional Encoding for Length Extrapolation","created":"2024-05-23","cited_by_count":31,"area":null},{"id":"2204.13154","title":"Attention Mechanism in Neural Networks: Where it Comes and Where it Goes","created":"2022-04-27","cited_by_count":29,"area":null},{"id":"2102.10801","title":"Neural Delay Differential Equations","created":"2021-02-22","cited_by_count":26,"area":null},{"id":"2501.02950","title":"Key-value memory in the brain","created":"2025-01-06","cited_by_count":24,"area":null},{"id":"2106.01950","title":"The Case for Translation-Invariant Self-Attention in Transformer-Based Language Models","created":"2021-06-03","cited_by_count":23,"area":null},{"id":"2106.10786","title":"ROPE: Reading Order Equivariant Positional Encoding for Graph-based Document Information Extraction","created":"2021-06-21","cited_by_count":22,"area":null},{"id":"2207.11464","title":"Learning Object Placement via Dual-path Graph Completion","created":"2022-07-23","cited_by_count":20,"area":null},{"id":"2502.02562","title":"Learning the RoPEs: Better 2D and 3D Position Encodings with STRING","created":"2025-02-04","cited_by_count":19,"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":"2203.09175","title":"Generalized Classification of Satellite Image Time Series with Thermal Positional Encoding","created":"2022-03-17","cited_by_count":14,"area":null},{"id":"2208.11445","title":"Induced Natural Language Rationales and Interleaved Markup Tokens Enable Extrapolation in Large Language Models","created":"2022-08-24","cited_by_count":10,"area":null},{"id":"2408.08506","title":"Ex3: Automatic Novel Writing by Extracting, Excelsior and Expanding","created":"2024-08-16","cited_by_count":10,"area":null},{"id":"2410.04798","title":"DAPE V2: Process Attention Score as Feature Map for Length Extrapolation","created":"2024-10-07","cited_by_count":10,"area":null},{"id":"2212.07514","title":"PulseImpute: A Novel Benchmark Task for Pulsative Physiological Signal Imputation","created":"2022-12-14","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":"2302.06459","title":"Encoding Sentence Position in Context-Aware Neural Machine Translation with Concatenation","created":"2023-02-13","cited_by_count":6,"area":null},{"id":"2309.10291","title":"Koopman Invertible Autoencoder: Leveraging Forward and Backward Dynamics for Temporal Modeling","created":"2023-09-19","cited_by_count":6,"area":null},{"id":"2208.09300","title":"Expressing Multivariate Time Series as Graphs with Time Series Attention Transformer","created":"2022-08-19","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":"2512.07805","title":"Group Representational Position Encoding","created":"2025-12-08","cited_by_count":5,"area":null},{"id":"2207.08412","title":"Multi-branch Cascaded Swin Transformers with Attention to k-space Sampling Pattern for Accelerated MRI Reconstruction","created":"2022-07-18","cited_by_count":4,"area":null},{"id":"2309.04840","title":"AnyPose: Anytime 3D Human Pose Forecasting via Neural Ordinary Differential Equations","created":"2023-09-09","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":"2111.06599","title":"PESTO: Switching Point based Dynamic and Relative Positional Encoding for Code-Mixed Languages","created":"2021-11-12","cited_by_count":3,"area":null},{"id":"2204.11045","title":"Investigating Neural Architectures by Synthetic Dataset Design","created":"2022-04-23","cited_by_count":3,"area":null},{"id":"2409.20092","title":"Continuous-Time Linear Positional Embedding for Irregular Time Series Forecasting","created":"2024-09-30","cited_by_count":3,"area":null},{"id":"2511.08368","title":"A Circular Argument : Does RoPE need to be Equivariant for Vision?","created":"2025-11-11","cited_by_count":3,"area":null},{"id":"2309.05270","title":"CONFLATOR: Incorporating Switching Point based Rotatory Positional Encodings for Code-Mixed Language Modeling","created":"2023-09-11","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":"2509.22259","title":"Rotary Position Encodings for Graphs","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2105.04888","title":"Hierarchical RNNs-Based Transformers MADDPG for Mixed Cooperative-Competitive Environments","created":"2021-05-11","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":"2406.03808","title":"Cross-variable Linear Integrated ENhanced Transformer for Photovoltaic power forecasting","created":"2024-06-06","cited_by_count":1,"area":null},{"id":"2506.14786","title":"PIPE: Physics-Informed Position Encoding for Alignment of Satellite Images and Time Series","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2508.10160","title":"Pre-trained Transformer-models using chronic invasive electrophysiology for symptom decoding without patient-individual training","created":"2025-08-13","cited_by_count":1,"area":null},{"id":"2509.22692","title":"Deep Learning Empowered Super-Resolution: A Comprehensive Survey and Future Prospects","created":"2025-09-19","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":"2204.08142","title":"Dynamic Position Encoding for Transformers","created":"2022-04-18","cited_by_count":0,"area":null},{"id":"2210.09871","title":"Sequence and Circle: Exploring the Relationship Between Patches","created":"2022-10-18","cited_by_count":0,"area":null},{"id":"2304.05310","title":"Neural Delay Differential Equations: System Reconstruction and Image Classification","created":"2023-04-11","cited_by_count":0,"area":null},{"id":"2504.18059","title":"POET: Prompt Offset Tuning for Continual Human Action Adaptation","created":"2025-04-25","cited_by_count":0,"area":null},{"id":"2511.06376","title":"Vocabulary In-Context Learning in Transformers: Benefits of Positional Encoding","created":"2025-11-09","cited_by_count":0,"area":null},{"id":"2511.12730","title":"Improving the Generalisation of Learned Reconstruction Frameworks","created":"2025-11-16","cited_by_count":0,"area":null},{"id":"2512.02465","title":"TabGRU: An Enhanced Design for Urban Rainfall Intensity Estimation Using Commercial Microwave Links","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2602.22274","title":"Positional-aware Spatio-Temporal Network for Large-Scale Traffic Prediction","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2605.30022","title":"Give it Space! Explicit Disentangling of Positional and Semantic Representations in Encoders","created":"2026-05-28","cited_by_count":0,"area":null}],"next_cursor":null}