{"total":34,"rows":[{"id":"2210.10340","title":"The Devil in Linear Transformer","created":"2022-10-19","cited_by_count":98,"area":null},{"id":"2406.02542","title":"Loki: Low-rank Keys for Efficient Sparse Attention","created":"2024-06-04","cited_by_count":89,"area":null},{"id":"2302.06461","title":"A Study on ReLU and Softmax in Transformer","created":"2023-02-13","cited_by_count":53,"area":null},{"id":"2407.15017","title":"Knowledge Mechanisms in Large Language Models: A Survey and Perspective","created":"2024-07-22","cited_by_count":51,"area":null},{"id":"2205.08078","title":"Unraveling Attention via Convex Duality: Analysis and Interpretations of Vision Transformers","created":"2022-05-17","cited_by_count":30,"area":null},{"id":"2207.13955","title":"Neural Architecture Search on Efficient Transformers and Beyond","created":"2022-07-28","cited_by_count":17,"area":null},{"id":"2109.12188","title":"Predicting Attention Sparsity in Transformers","created":"2021-09-24","cited_by_count":13,"area":null},{"id":"2310.02260","title":"TransRadar: Adaptive-Directional Transformer for Real-Time Multi-View Radar Semantic Segmentation","created":"2023-10-03","cited_by_count":9,"area":null},{"id":"2402.02362","title":"Unification of Symmetries Inside Neural Networks: Transformer, Feedforward and Neural ODE","created":"2024-02-04","cited_by_count":7,"area":null},{"id":"2403.17753","title":"CCDSReFormer: Traffic Flow Prediction with a Criss-Crossed Dual-Stream Enhanced Rectified Transformer Model","created":"2024-03-26","cited_by_count":5,"area":null},{"id":"2601.12145","title":"Threshold Differential Attention for Sink-Free, Ultra-Sparse, and Non-Dispersive Language Modeling","created":"2026-01-17","cited_by_count":5,"area":null},{"id":"2211.09458","title":"Abstractive Summarization Guided by Latent Hierarchical Document Structure","created":"2022-11-17","cited_by_count":4,"area":null},{"id":"2401.02721","title":"A Cost-Efficient FPGA Implementation of Tiny Transformer Model using Neural ODE","created":"2024-01-05","cited_by_count":4,"area":null},{"id":"2111.06832","title":"Speeding Up Entmax","created":"2021-11-12","cited_by_count":3,"area":null},{"id":"2512.10282","title":"Neuronal Attention Circuit (NAC) for Representation Learning","created":"2025-12-11","cited_by_count":3,"area":null},{"id":"2602.12601","title":"HyperMLP: An Integrated Perspective for Sequence Modeling","created":"2026-02-13","cited_by_count":3,"area":null},{"id":"2211.00562","title":"Leveraging commonsense for object localisation in partial scenes","created":"2022-11-01","cited_by_count":2,"area":null},{"id":"2312.07280","title":"Towards Equipping Transformer with the Ability of Systematic Compositionality","created":"2023-12-12","cited_by_count":2,"area":null},{"id":"2312.10890","title":"Low-latency Space-time Supersampling for Real-time Rendering","created":"2023-12-18","cited_by_count":2,"area":null},{"id":"2502.08363","title":"Top-Theta Attention: Sparsifying Transformers by Compensated Thresholding","created":"2025-02-12","cited_by_count":2,"area":null},{"id":"2402.07680","title":"AYDIV: Adaptable Yielding 3D Object Detection via Integrated Contextual Vision Transformer","created":"2024-02-12","cited_by_count":1,"area":null},{"id":"2503.23174","title":"TRA: Better Length Generalisation with Threshold Relative Attention","created":"2025-03-29","cited_by_count":1,"area":null},{"id":"2507.15798","title":"Exploring Superposition and Interference in State-of-the-Art Low-Parameter Vision Models","created":"2025-07-21","cited_by_count":1,"area":null},{"id":"2311.15402","title":"Learning Section Weights for Multi-Label Document Classification","created":"2023-11-26","cited_by_count":0,"area":null},{"id":"2502.00585","title":"Converting Transformers into DGNNs Form","created":"2025-02-01","cited_by_count":0,"area":null},{"id":"2503.01564","title":"Attention Condensation via Sparsity Induced Regularized Training","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2505.17683","title":"Dual Attention Residual U-Net for Accurate Brain Ultrasound Segmentation in IVH Detection","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2510.11789","title":"Minimax Rates for Learning Pairwise Interactions in Attention-Style Models","created":"2025-10-13","cited_by_count":0,"area":null},{"id":"2602.20300","title":"What Makes a Good Query? Measuring the Impact of Human-Confusing Linguistic Features on LLM Performance","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2604.02292","title":"Taming the Exponential: A Fast Softmax Surrogate for Integer-Native Edge Inference","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2606.31609","title":"Learning Structurally Consistent Representations for Multi-View Radar Semantic Segmentation","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.13925","title":"Thresholded Cross-Attention for Reliable Intensity-Chromaticity Fusion in Low-Light Image Enhancement","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2608.21174","title":"From Attention Masks to Inert Zero-Vector Tokens: OAttention and O-Closure for Token Dynamics","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.33591","title":"Pretraining Transformers with Quantized Softmax in Attention","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}