{"total":103,"rows":[{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"area":null},{"id":"2110.07875","title":"Graph Neural Networks with Learnable Structural and Positional Representations","created":"2021-10-15","cited_by_count":333,"area":null},{"id":"2311.04934","title":"Prompt Cache: Modular Attention Reuse for Low-Latency Inference","created":"2023-11-07","cited_by_count":268,"area":null},{"id":"2212.10554","title":"A Length-Extrapolatable Transformer","created":"2022-12-20","cited_by_count":127,"area":null},{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"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":"2203.16896","title":"CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow","created":"2022-03-31","cited_by_count":82,"area":null},{"id":"2405.18719","title":"Contextual Position Encoding: Learning to Count What's Important","created":"2024-05-29","cited_by_count":54,"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":"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":"2110.01191","title":"Molformer: Motif-based Transformer on 3D Heterogeneous Molecular Graphs","created":"2021-10-04","cited_by_count":44,"area":null},{"id":"2404.11735","title":"Learning with 3D rotations, a hitchhiker's guide to SO(3)","created":"2024-04-17","cited_by_count":42,"area":null},{"id":"2109.05644","title":"SHAPE: Shifted Absolute Position Embedding for Transformers","created":"2021-09-13","cited_by_count":37,"area":null},{"id":"2307.07982","title":"A Survey of Techniques for Optimizing Transformer Inference","created":"2023-07-16","cited_by_count":35,"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":"2205.12551","title":"Masked Jigsaw Puzzle: A Versatile Position Embedding for Vision Transformers","created":"2022-05-25","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":"2207.07611","title":"Position Prediction as an Effective Pretraining Strategy","created":"2022-07-15","cited_by_count":24,"area":null},{"id":"2403.06949","title":"Materials science in the era of large language models: a perspective","created":"2024-03-11","cited_by_count":24,"area":null},{"id":"2302.11070","title":"Universal Morphology Control via Contextual Modulation","created":"2023-02-22","cited_by_count":23,"area":null},{"id":"2404.09554","title":"Explainable Generative AI (GenXAI): A Survey, Conceptualization, and Research Agenda","created":"2024-04-15","cited_by_count":22,"area":null},{"id":"2309.03576","title":"DropPos: Pre-Training Vision Transformers by Reconstructing Dropped Positions","created":"2023-09-07","cited_by_count":19,"area":null},{"id":"2301.05453","title":"It's Just a Matter of Time: Detecting Depression with Time-Enriched Multimodal Transformers","created":"2023-01-13","cited_by_count":18,"area":null},{"id":"2507.00191","title":"Beyond Sensor Data: Foundation Models of Behavioral Data from Wearables Improve Health Predictions","created":"2025-06-30","cited_by_count":18,"area":null},{"id":"2405.09285","title":"Positional Knowledge is All You Need: Position-induced Transformer (PiT) for Operator Learning","created":"2024-05-15","cited_by_count":17,"area":null},{"id":"2401.09074","title":"Code Simulation Challenges for Large Language Models","created":"2024-01-17","cited_by_count":15,"area":null},{"id":"2103.04037","title":"Perspectives and Prospects on Transformer Architecture for Cross-Modal Tasks with Language and Vision","created":"2021-03-06","cited_by_count":14,"area":null},{"id":"2203.03047","title":"Recent Advances in Neural Text Generation: A Task-Agnostic Survey","created":"2022-03-06","cited_by_count":14,"area":null},{"id":"2302.09268","title":"Bag of Tricks for Effective Language Model Pretraining and Downstream Adaptation: A Case Study on GLUE","created":"2023-02-18","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":"2601.07220","title":"The Roots of Performance Disparity in Multilingual Language Models: Intrinsic Modeling Difficulty or Design Choices?","created":"2026-01-12","cited_by_count":11,"area":null},{"id":"2104.14729","title":"CoSformer: Detecting Co-Salient Object with Transformers","created":"2021-04-30","cited_by_count":10,"area":null},{"id":"2109.14017","title":"Shaking Syntactic Trees on the Sesame Street: Multilingual Probing with Controllable Perturbations","created":"2021-09-28","cited_by_count":10,"area":null},{"id":"2310.11984","title":"From Interpolation to Extrapolation: Complete Length Generalization for Arithmetic Transformers","created":"2023-10-18","cited_by_count":10,"area":null},{"id":"2312.16045","title":"Algebraic Positional Encodings","created":"2023-12-26","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":"2312.09041","title":"Graph Neural Networks with Diverse Spectral Filtering","created":"2023-12-14","cited_by_count":9,"area":null},{"id":"2505.18907","title":"Stronger Enforcement of Instruction Hierarchy via Augmented Intermediate Representations","created":"2025-05-25","cited_by_count":9,"area":"safety"},{"id":"2511.20038","title":"Softmax Transformers are Turing-Complete","created":"2025-11-25","cited_by_count":9,"area":"lr"},{"id":"2502.03568","title":"Code Simulation as a Proxy for High-order Tasks in Large Language Models","created":"2025-02-05","cited_by_count":7,"area":null},{"id":"2308.05051","title":"PAT: Position-Aware Transformer for Dense Multi-Label Action Detection","created":"2023-08-09","cited_by_count":6,"area":null},{"id":"2401.07105","title":"Graph Language Models","created":"2024-01-13","cited_by_count":6,"area":null},{"id":"2506.02138","title":"Revisiting LRP: Positional Attribution as the Missing Ingredient for Transformer Explainability","created":"2025-06-02","cited_by_count":6,"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":"2310.17936","title":"Transformers as Graph-to-Graph Models","created":"2023-10-27","cited_by_count":5,"area":null},{"id":"2402.09808","title":"Knowledge of Pretrained Language Models on Surface Information of Tokens","created":"2024-02-15","cited_by_count":5,"area":null},{"id":"2405.17509","title":"Reference Neural Operators: Learning the Smooth Dependence of Solutions of PDEs on Geometric Deformations","created":"2024-05-27","cited_by_count":5,"area":null},{"id":"2405.18548","title":"Transformer Encoder Satisfiability: Complexity and Impact on Formal Reasoning","created":"2024-05-28","cited_by_count":5,"area":null},{"id":"2407.16604","title":"Shared Imagination: LLMs Hallucinate Alike","created":"2024-07-23","cited_by_count":5,"area":null},{"id":"2410.21013","title":"Frequency matters: Modeling irregular morphological patterns in Spanish with Transformers","created":"2024-10-28","cited_by_count":5,"area":null},{"id":"2211.04427","title":"Word Order Matters when you Increase Masking","created":"2022-11-08","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":"2506.02306","title":"CACTI: Leveraging Copy Masking and Contextual Information to Improve Tabular Data Imputation","created":"2025-06-02","cited_by_count":4,"area":null},{"id":"2204.11045","title":"Investigating Neural Architectures by Synthetic Dataset Design","created":"2022-04-23","cited_by_count":3,"area":null},{"id":"2403.04012","title":"Temporal Cross-Attention for Dynamic Embedding and Tokenization of Multimodal Electronic Health Records","created":"2024-03-06","cited_by_count":3,"area":null},{"id":"2403.17698","title":"MEP: Multiple Kernel Learning Enhancing Relative Positional Encoding Length Extrapolation","created":"2024-03-26","cited_by_count":3,"area":null},{"id":"2407.13238","title":"Transformers with Stochastic Competition for Tabular Data Modelling","created":"2024-07-18","cited_by_count":3,"area":null},{"id":"2407.19784","title":"Survey and Taxonomy: The Role of Data-Centric AI in Transformer-Based Time Series Forecasting","created":"2024-07-29","cited_by_count":3,"area":null},{"id":"2412.15302","title":"Tokenphormer: Structure-aware Multi-token Graph Transformer for Node Classification","created":"2024-12-19","cited_by_count":3,"area":null},{"id":"2505.23086","title":"Equivariant Spherical Transformer for Efficient Molecular Modeling","created":"2025-05-29","cited_by_count":3,"area":null},{"id":"2603.07461","title":"The Dual-Stream Transformer: Channelized Architecture for Interpretable Language Modeling","created":"2026-03-08","cited_by_count":3,"area":null},{"id":"2302.05900","title":"Investigating the Effect of Relative Positional Embeddings on AMR-to-Text Generation with Structural Adapters","created":"2023-02-12","cited_by_count":2,"area":null},{"id":"2411.16917","title":"Are Transformers Truly Foundational for Robotics?","created":"2024-11-25","cited_by_count":2,"area":null},{"id":"2602.14100","title":"Character-aware Transformers Learn an Irregular Morphological Pattern Yet None Generalize Like Humans","created":"2026-02-15","cited_by_count":2,"area":null},{"id":"2203.05338","title":"TrueType Transformer: Character and Font Style Recognition in Outline Format","created":"2022-03-10","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":"2212.05262","title":"Position Embedding Needs an Independent Layer Normalization","created":"2022-12-10","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":"2310.12864","title":"The Locality and Symmetry of Positional Encodings","created":"2023-10-19","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":"2402.02164","title":"Hierarchical Structure Enhances the Convergence and Generalizability of Linear Molecular Representation","created":"2024-02-03","cited_by_count":1,"area":null},{"id":"2409.05884","title":"Integrating the Expected Future in Load Forecasts with Contextually Enhanced Transformer Models","created":"2024-08-26","cited_by_count":1,"area":null},{"id":"2502.02659","title":"A Training-Free Length Extrapolation Approach for LLMs: Greedy Attention Logit Interpolation (GALI)","created":"2025-02-04","cited_by_count":1,"area":null},{"id":"2504.17069","title":"Distilling Specialized Orders for Visual Generation","created":"2025-04-23","cited_by_count":1,"area":null},{"id":"2509.21042","title":"LayerNorm Induces Recency Bias in Transformer Decoders","created":"2025-09-25","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":"2511.08888","title":"Weaver: Kronecker Product Approximations of Spatiotemporal Attention for Traffic Network Forecasting","created":"2025-11-12","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":"2208.10247","title":"Generalized Attention Mechanism and Relative Position for Transformer","created":"2022-07-24","cited_by_count":0,"area":null},{"id":"2212.07126","title":"Explainability of Text Processing and Retrieval Methods: A Survey","created":"2022-12-14","cited_by_count":0,"area":null},{"id":"2307.07975","title":"Pseudo-rigid body networks: learning interpretable deformable object dynamics from partial observations","created":"2023-07-16","cited_by_count":0,"area":null},{"id":"2401.01233","title":"GEN: A Practical Alternative to Graph Transformers for Long-Range Graph Modeling","created":"2024-01-02","cited_by_count":0,"area":null},{"id":"2401.15089","title":"Accelerating Material Property Prediction using Generically Complete Isometry Invariants","created":"2024-01-22","cited_by_count":0,"area":null},{"id":"2405.04767","title":"Test-Time Augmentation for Traveling Salesperson Problem","created":"2024-05-08","cited_by_count":0,"area":null},{"id":"2406.06187","title":"An Effective-Efficient Approach for Dense Multi-Label Action Detection","created":"2024-06-10","cited_by_count":0,"area":null},{"id":"2411.13867","title":"Generative Fuzzy System for Sequence Generation","created":"2024-11-21","cited_by_count":0,"area":null},{"id":"2504.19239","title":"The effect of the number of parameters and the number of local feature patches on loss landscapes in distributed quantum neural networks","created":"2025-04-27","cited_by_count":0,"area":null},{"id":"2507.03047","title":"Enhancing Temporal Sensitivity of Large Language Model for Recommendation with Counterfactual Tuning","created":"2025-07-03","cited_by_count":0,"area":"lr"},{"id":"2508.06641","title":"Fractal Language Modelling by Universal Sequence Maps (USM)","created":"2025-08-08","cited_by_count":0,"area":null},{"id":"2508.18598","title":"What do language models model? Transformers, automata, and the format of thought","created":"2025-08-26","cited_by_count":0,"area":"lr"},{"id":"2508.20211","title":"What can we learn from signals and systems in a transformer? Insights for probabilistic modeling and inference architecture","created":"2025-08-27","cited_by_count":0,"area":null},{"id":"2509.15210","title":"Explicit Context-Driven Neural Acoustic Modeling for High-Fidelity RIR Generation","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2511.19364","title":"Neural surrogates for designing gravitational wave detectors","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2512.19323","title":"Alternative positional encoding functions for neural transformers","created":"2025-12-22","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":"2602.05006","title":"Enhanced QKNorm normalization for neural transformers with the Lp norm","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2604.18603","title":"Dual Triangle Attention: Effective Bidirectional Attention Without Positional Embeddings","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2605.23025","title":"World Machine: Towards Generative World Modeling for Time-Series","created":"2026-05-21","cited_by_count":0,"area":"wm"},{"id":"2606.25293","title":"Communicability-Inspired Positional Encoding (CIPE)","created":"2026-06-24","cited_by_count":0,"area":null}],"next_cursor":"100"}