{"total":14,"rows":[{"id":"2106.04554","title":"A Survey of Transformers","created":"2021-06-08","cited_by_count":401,"area":null},{"id":"2310.19089","title":"Pushdown Layers: Encoding Recursive Structure in Transformer Language Models","created":"2023-10-29","cited_by_count":19,"area":null},{"id":"2310.12956","title":"Eureka-Moments in Transformers: Multi-Step Tasks Reveal Softmax Induced Optimization Problems","created":"2023-10-19","cited_by_count":14,"area":null},{"id":"2201.12475","title":"Retroformer: Pushing the Limits of Interpretable End-to-end Retrosynthesis Transformer","created":"2022-01-29","cited_by_count":8,"area":null},{"id":"2305.15775","title":"Concept-Centric Transformers: Enhancing Model Interpretability through Object-Centric Concept Learning within a Shared Global Workspace","created":"2023-05-25","cited_by_count":7,"area":null},{"id":"2204.02922","title":"Paying More Attention to Self-attention: Improving Pre-trained Language Models via Attention Guiding","created":"2022-04-06","cited_by_count":6,"area":null},{"id":"2302.12441","title":"MUX-PLMs: Data Multiplexing for High-throughput Language Models","created":"2023-02-24","cited_by_count":4,"area":null},{"id":"2208.10491","title":"Improving Speech Emotion Recognition Through Focus and Calibration Attention Mechanisms","created":"2022-08-21","cited_by_count":3,"area":null},{"id":"2411.18885","title":"Sneaking Syntax into Transformer Language Models with Tree Regularization","created":"2024-11-28","cited_by_count":3,"area":null},{"id":"2402.16790","title":"Beyond Self-learned Attention: Mitigating Attention Bias in Transformer-based Models Using Attention Guidance","created":"2024-02-26","cited_by_count":1,"area":null},{"id":"2605.15562","title":"GiLT: Augmenting Transformer Language Models with Dependency Graphs","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2206.07587","title":"Cross-lingual AMR Aligner: Paying Attention to Cross-Attention","created":"2022-06-15","cited_by_count":0,"area":null},{"id":"2501.12434","title":"ConfRetro: a 3D-aware template-free method for enhancing retrosynthesis via molecular conformer information","created":"2025-01-21","cited_by_count":0,"area":null},{"id":"2510.16588","title":"Copy-Augmented Representation for Structure Invariant Template-Free Retrosynthesis","created":"2025-10-18","cited_by_count":0,"area":null}],"next_cursor":null}