{"total":40,"rows":[{"id":"2106.04554","title":"A Survey of Transformers","created":"2021-06-08","cited_by_count":401,"area":null},{"id":"2103.02143","title":"Random Feature Attention","created":"2021-03-03","cited_by_count":354,"area":null},{"id":"2105.03824","title":"FNet: Mixing Tokens with Fourier Transforms","created":"2021-05-09","cited_by_count":347,"area":null},{"id":"2202.01381","title":"ETSformer: Exponential Smoothing Transformers for Time-series Forecasting","created":"2022-02-03","cited_by_count":148,"area":null},{"id":"2201.05273","title":"Pretrained Language Models for Text Generation: A Survey","created":"2022-01-14","cited_by_count":122,"area":null},{"id":"2206.04301","title":"Unveiling Transformers with LEGO: a synthetic reasoning task","created":"2022-06-09","cited_by_count":106,"area":null},{"id":"2102.11090","title":"Position Information in Transformers: An Overview","created":"2021-02-22","cited_by_count":103,"area":null},{"id":"2103.13076","title":"Finetuning Pretrained Transformers into RNNs","created":"2021-03-24","cited_by_count":96,"area":null},{"id":"2104.08771","title":"Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation","created":"2021-04-18","cited_by_count":74,"area":null},{"id":"2110.02488","title":"ABC: Attention with Bounded-memory Control","created":"2021-10-06","cited_by_count":36,"area":null},{"id":"2211.03495","title":"How Much Does Attention Actually Attend? Questioning the Importance of Attention in Pretrained Transformers","created":"2022-11-07","cited_by_count":21,"area":null},{"id":"2109.05244","title":"Modeling Concentrated Cross-Attention for Neural Machine Translation with Gaussian Mixture Model","created":"2021-09-11","cited_by_count":18,"area":null},{"id":"2208.06551","title":"Exploiting Multiple Sequence Lengths in Fast End to End Training for Image Captioning","created":"2022-08-13","cited_by_count":18,"area":null},{"id":"2210.12463","title":"EtriCA: Event-Triggered Context-Aware Story Generation Augmented by Cross Attention","created":"2022-10-22","cited_by_count":17,"area":null},{"id":"2108.01988","title":"Sparse Continuous Distributions and Fenchel-Young Losses","created":"2021-08-04","cited_by_count":14,"area":null},{"id":"2203.01178","title":"DCT-Former: Efficient Self-Attention with Discrete Cosine Transform","created":"2022-03-02","cited_by_count":12,"area":null},{"id":"2204.05424","title":"A Call for Clarity in Beam Search: How It Works and When It Stops","created":"2022-04-11","cited_by_count":10,"area":null},{"id":"2206.12608","title":"Adversarial Self-Attention for Language Understanding","created":"2022-06-25","cited_by_count":8,"area":null},{"id":"2103.01009","title":"Snowflake: Scaling GNNs to High-Dimensional Continuous Control via Parameter Freezing","created":"2021-03-01","cited_by_count":7,"area":null},{"id":"2109.00301","title":"$\\infty$-former: Infinite Memory Transformer","created":"2021-09-01","cited_by_count":7,"area":null},{"id":"2104.04692","title":"Not All Attention Is All You Need","created":"2021-04-10","cited_by_count":5,"area":null},{"id":"2106.06411","title":"Zero-Shot Controlled Generation with Encoder-Decoder Transformers","created":"2021-06-11","cited_by_count":5,"area":null},{"id":"2209.12816","title":"Fast-FNet: Accelerating Transformer Encoder Models via Efficient Fourier Layers","created":"2022-09-26","cited_by_count":5,"area":null},{"id":"2311.11271","title":"A Cross-Attention Augmented Model for Event-Triggered Context-Aware Story Generation","created":"2023-11-19","cited_by_count":5,"area":null},{"id":"2210.01989","title":"WavSpA: Wavelet Space Attention for Boosting Transformers' Long Sequence Learning Ability","created":"2022-10-05","cited_by_count":3,"area":null},{"id":"2407.02423","title":"On the Anatomy of Attention","created":"2024-07-02","cited_by_count":3,"area":null},{"id":"2401.11143","title":"Density Adaptive Attention is All You Need: Robust Parameter-Efficient Fine-Tuning Across Multiple Modalities","created":"2024-01-20","cited_by_count":2,"area":null},{"id":"2110.08536","title":"Sparse Distillation: Speeding Up Text Classification by Using Bigger Student Models","created":"2021-10-16","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":"2101.06397","title":"To Understand Representation of Layer-aware Sequence Encoders as Multi-order-graph","created":"2021-01-16","cited_by_count":0,"area":null},{"id":"2105.14850","title":"Cascaded Head-colliding Attention","created":"2021-05-31","cited_by_count":0,"area":null},{"id":"2302.00340","title":"Attention Link: An Efficient Attention-Based Low Resource Machine Translation Architecture","created":"2023-02-01","cited_by_count":0,"area":null},{"id":"2402.16470","title":"Unveiling Vulnerability of Self-Attention","created":"2024-02-26","cited_by_count":0,"area":null},{"id":"2403.18228","title":"Fourier or Wavelet bases as counterpart self-attention in spikformer for efficient visual classification","created":"2024-03-27","cited_by_count":0,"area":null},{"id":"2409.13291","title":"Localized Gaussians as Self-Attention Weights for Point Clouds Correspondence","created":"2024-09-20","cited_by_count":0,"area":null},{"id":"2510.18810","title":"When LRP Diverges from Leave-One-Out in Transformers","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2512.13487","title":"Advancing Bangla Machine Translation Through Informal Datasets","created":"2025-12-15","cited_by_count":0,"area":null},{"id":"2602.22368","title":"EyeLayer: Integrating Human Attention Patterns into LLM-Based Code Summarization","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2609.34650","title":"When Can Attention Heads Be Statically Defined?","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.01831","title":"Pooling Helps, Learned Weighting Hurts In-Context: Decomposing Group Attention","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}