{"total":15,"rows":[{"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":"2407.19394","title":"Depth-Wise Convolutions in Vision Transformers for Efficient Training on Small Datasets","created":"2024-07-28","cited_by_count":14,"area":null},{"id":"2504.16275","title":"Quantum Doubly Stochastic Transformers","created":"2025-04-22","cited_by_count":6,"area":null},{"id":"2305.07931","title":"GSB: Group Superposition Binarization for Vision Transformer with Limited Training Samples","created":"2023-05-13","cited_by_count":4,"area":null},{"id":"2506.02843","title":"Random Registers for Cross-Domain Few-Shot Learning","created":"2025-06-03","cited_by_count":4,"area":null},{"id":"2506.03110","title":"Revisiting Continuity of Image Tokens for Cross-domain Few-shot Learning","created":"2025-06-03","cited_by_count":3,"area":null},{"id":"2305.16661","title":"Gender, Smoking History and Age Prediction from Laryngeal Images","created":"2023-05-26","cited_by_count":2,"area":null},{"id":"2401.15175","title":"Kitchen Food Waste Image Segmentation and Classification for Compost Nutrients Estimation","created":"2024-01-26","cited_by_count":2,"area":null},{"id":"2403.18180","title":"Multi-Layer Dense Attention Decoder for Polyp Segmentation","created":"2024-03-27","cited_by_count":2,"area":null},{"id":"2410.04801","title":"Improving Image Clustering with Artifacts Attenuation via Inference-Time Attention Engineering","created":"2024-10-07","cited_by_count":2,"area":null},{"id":"2410.14874","title":"Beyond Isolated Heads: Multi-Overlapped-Head Self-Attention for Vision Transformers","created":"2024-10-18","cited_by_count":1,"area":null},{"id":"2511.01292","title":"Optimal Attention Temperature Improves the Robustness of In-Context Learning under Distribution Shift in High Dimensions","created":"2025-11-03","cited_by_count":1,"area":null},{"id":"2504.01348","title":"Prompt-Guided Attention Head Selection for Focus-Oriented Image Retrieval","created":"2025-04-02","cited_by_count":0,"area":null},{"id":"2507.21256","title":"Tracking Moose using Aerial Object Detection","created":"2025-07-28","cited_by_count":0,"area":null},{"id":"2603.18585","title":"HAViT: Historical Attention Vision Transformer","created":"2026-03-19","cited_by_count":0,"area":null}],"next_cursor":null}