{"total":52,"rows":[{"id":"2102.11090","title":"Position Information in Transformers: An Overview","created":"2021-02-22","cited_by_count":103,"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":"2205.11961","title":"ATTEMPT: Parameter-Efficient Multi-task Tuning via Attentional Mixtures of Soft Prompts","created":"2022-05-24","cited_by_count":85,"area":null},{"id":"2202.01338","title":"Regression Transformer: Concurrent sequence regression and generation for molecular language modeling","created":"2022-02-01","cited_by_count":50,"area":null},{"id":"2212.03229","title":"Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning","created":"2022-12-06","cited_by_count":49,"area":null},{"id":"2205.01138","title":"Transformers in Time-series Analysis: A Tutorial","created":"2022-04-28","cited_by_count":46,"area":null},{"id":"2104.08698","title":"A Simple and Effective Positional Encoding for Transformers","created":"2021-04-18","cited_by_count":37,"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":"2109.06096","title":"The Grammar-Learning Trajectories of Neural Language Models","created":"2021-09-13","cited_by_count":36,"area":null},{"id":"2206.01078","title":"Deep Transformer Q-Networks for Partially Observable Reinforcement Learning","created":"2022-06-02","cited_by_count":36,"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":"2203.10995","title":"Word Order Does Matter (And Shuffled Language Models Know It)","created":"2022-03-21","cited_by_count":32,"area":null},{"id":"2408.14511","title":"Unveiling the Statistical Foundations of Chain-of-Thought Prompting Methods","created":"2024-08-25","cited_by_count":29,"area":"lr"},{"id":"2204.13346","title":"UniTE: Unified Translation Evaluation","created":"2022-04-28","cited_by_count":28,"area":null},{"id":"2207.06983","title":"Multitrack Music Transformer","created":"2022-07-14","cited_by_count":28,"area":null},{"id":"2109.13006","title":"RuleBert: Teaching Soft Rules to Pre-trained Language Models","created":"2021-09-24","cited_by_count":25,"area":null},{"id":"2203.14666","title":"Federated Learning with Position-Aware Neurons","created":"2022-03-28","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":"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":"2310.04861","title":"Uncovering hidden geometry in Transformers via disentangling position and context","created":"2023-10-07","cited_by_count":18,"area":null},{"id":"2210.12574","title":"The Curious Case of Absolute Position Embeddings","created":"2022-10-23","cited_by_count":17,"area":null},{"id":"2302.02108","title":"Knowledge Distillation in Vision Transformers: A Critical Review","created":"2023-02-04","cited_by_count":13,"area":"distill"},{"id":"2401.02746","title":"Reading Between the Frames: Multi-Modal Depression Detection in Videos from Non-Verbal Cues","created":"2024-01-05","cited_by_count":11,"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":"2509.05218","title":"HoPE: Hyperbolic Rotary Positional Encoding for Stable Long-Range Dependency Modeling in Large Language Models","created":"2025-09-05","cited_by_count":10,"area":null},{"id":"2510.16670","title":"All You Need is One: Capsule Prompt Tuning with a Single Vector","created":"2025-10-19","cited_by_count":8,"area":null},{"id":"2203.13491","title":"Striking a Balance: Alleviating Inconsistency in Pre-trained Models for Symmetric Classification Tasks","created":"2022-03-25","cited_by_count":6,"area":null},{"id":"2104.08673","title":"\"Average\" Approximates \"First Principal Component\"? An Empirical Analysis on Representations from Neural Language Models","created":"2021-04-18","cited_by_count":4,"area":null},{"id":"2210.12078","title":"Experiencer-Specific Emotion and Appraisal Prediction","created":"2022-10-21","cited_by_count":4,"area":null},{"id":"2305.10046","title":"Probing the Role of Positional Information in Vision-Language Models","created":"2023-05-17","cited_by_count":4,"area":"mllm"},{"id":"2109.00442","title":"Position Masking for Improved Layout-Aware Document Understanding","created":"2021-09-01","cited_by_count":3,"area":null},{"id":"2402.06367","title":"TEE4EHR: Transformer Event Encoder for Better Representation Learning in Electronic Health Records","created":"2024-02-09","cited_by_count":3,"area":null},{"id":"2410.04703","title":"Neural Fourier Modelling: A Highly Compact Approach to Time-Series Analysis","created":"2024-10-07","cited_by_count":3,"area":null},{"id":"2502.12717","title":"Learning the symmetric group: large from small","created":"2025-02-18","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":"2402.19160","title":"Effective Message Hiding with Order-Preserving Mechanisms","created":"2024-02-29","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":"2405.17333","title":"Generating Accurate Synthetic Survival Data by Conditioning on Outcomes","created":"2024-05-27","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":"2212.05262","title":"Position Embedding Needs an Independent Layer Normalization","created":"2022-12-10","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":"2310.12864","title":"The Locality and Symmetry of Positional Encodings","created":"2023-10-19","cited_by_count":1,"area":null},{"id":"2510.03156","title":"Neural Correlates of Language Models Are Specific to Human Language","created":"2025-10-03","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":"2112.06166","title":"Topic Detection and Tracking with Time-Aware Document Embeddings","created":"2021-12-12","cited_by_count":0,"area":null},{"id":"2306.13817","title":"The Double Helix inside the NLP Transformer","created":"2023-06-23","cited_by_count":0,"area":null},{"id":"2407.02793","title":"Learning Positional Attention for Sequential Recommendation","created":"2024-07-03","cited_by_count":0,"area":null},{"id":"2408.03404","title":"Set2Seq Transformer: Temporal and Position-Aware Set Representations for Sequential Multiple-Instance Learning","created":"2024-08-06","cited_by_count":0,"area":null},{"id":"2502.09503","title":"AttentionSmithy: A Modular Framework for Rapid Transformer Development and Customization","created":"2025-02-13","cited_by_count":0,"area":null},{"id":"2507.08835","title":"Representation learning with a transformer by contrastive learning for money laundering detection","created":"2025-07-07","cited_by_count":0,"area":null},{"id":"2511.19118","title":"A symbolic Perl algorithm for the unification of Nahuatl word spellings","created":"2025-11-24","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}