{"total":15,"rows":[{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897,"area":null},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2310.11685","title":"Why Softmax Attention Outperforms Linear Attention","created":"2023-10-18","cited_by_count":15,"area":null},{"id":"2402.19052","title":"Exploring the Efficacy of Large Language Models in Summarizing Mental Health Counseling Sessions: A Benchmark Study","created":"2024-02-29","cited_by_count":13,"area":null},{"id":"2203.10694","title":"FAR: Fourier Aerial Video Recognition","created":"2022-03-21","cited_by_count":10,"area":null},{"id":"2211.15595","title":"FsaNet: Frequency Self-attention for Semantic Segmentation","created":"2022-11-28","cited_by_count":10,"area":null},{"id":"2502.07962","title":"ESPFormer: Doubly-Stochastic Attention with Expected Sliced Transport Plans","created":"2025-02-11","cited_by_count":10,"area":null},{"id":"2301.04791","title":"Self-Attention Amortized Distributional Projection Optimization for Sliced Wasserstein Point-Cloud Reconstruction","created":"2023-01-12","cited_by_count":7,"area":null},{"id":"2402.00743","title":"Theoretical Understanding of In-Context Learning in Shallow Transformers with Unstructured Data","created":"2024-02-01","cited_by_count":5,"area":null},{"id":"2502.10760","title":"Why is prompting hard? Understanding prompts on binary sequence predictors","created":"2025-02-15","cited_by_count":4,"area":null},{"id":"2509.24169","title":"Task Vectors, Learned Not Extracted: Performance Gains and Mechanistic Insight","created":"2025-09-29","cited_by_count":3,"area":null},{"id":"2409.00068","title":"An alternative formulation of attention pooling function in translation","created":"2024-08-23","cited_by_count":1,"area":null},{"id":"2412.00546","title":"Rank It, Then Ask It: Input Reranking for Maximizing the Performance of LLMs on Symmetric Tasks","created":"2024-11-30","cited_by_count":0,"area":null},{"id":"2506.02212","title":"Leveraging Natural Language Processing to Unravel the Mystery of Life: A Review of NLP Approaches in Genomics, Transcriptomics, and Proteomics","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2608.09468","title":"MixFormer: Linear Transformer with Mixture of Memory Experts","created":"2026-08-10","cited_by_count":0,"area":null}],"next_cursor":null}