{"total":22,"rows":[{"id":"2503.23844","title":"FlexiMo: A Flexible Remote Sensing Foundation Model","created":"2025-03-31","cited_by_count":24,"area":null},{"id":"2505.04601","title":"OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning","created":"2025-05-07","cited_by_count":16,"area":null},{"id":"2511.19515","title":"Fewer Tokens, Greater Scaling: Self-Adaptive Visual Bases for Efficient and Expansive Representation Learning","created":"2025-11-24","cited_by_count":16,"area":null},{"id":"2602.08071","title":"ViT-5: Vision Transformers for The Mid-2020s","created":"2026-02-08","cited_by_count":9,"area":null},{"id":"2504.00037","title":"ViT-Linearizer: Distilling Quadratic Knowledge into Linear-Time Vision Models","created":"2025-03-30","cited_by_count":5,"area":null},{"id":"2507.09264","title":"Overtone: Cyclic Patch Modulation for Clean, Efficient, and Flexible Physics Emulators","created":"2025-07-12","cited_by_count":5,"area":null},{"id":"2604.16429","title":"(Sparse) Attention to the Details: Preserving Spectral Fidelity in ML-based Weather Forecasting Models","created":"2026-04-06","cited_by_count":5,"area":null},{"id":"2509.16875","title":"Towards Interpretable and Efficient Attention: Compressing All by Contracting a Few","created":"2025-09-21","cited_by_count":2,"area":null},{"id":"2511.08704","title":"Rethinking Generative Image Pretraining: How Far Are We From Scaling Up Next-Pixel Prediction?","created":"2025-11-11","cited_by_count":2,"area":null},{"id":"2511.18105","title":"AdaPerceiver: Transformers with Adaptive Width, Depth, and Tokens","created":"2025-11-22","cited_by_count":1,"area":null},{"id":"2601.15516","title":"DeltaDorsal: Enhancing Hand Pose Estimation with Dorsal Features in Egocentric Views","created":"2026-01-21","cited_by_count":1,"area":null},{"id":"2603.04807","title":"Does Sparse Connectivity Improve Generalization? Convolutional Networks Below the Edge of Stability","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2604.07340","title":"TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders","created":"2026-04-08","cited_by_count":1,"area":null},{"id":"2605.17340","title":"Olivia: Harmonizing Time Series Foundation Models with Power Spectral Density","created":"2026-05-17","cited_by_count":1,"area":null},{"id":"2509.09722","title":"Improving MLLM Historical Record Extraction with Test-Time Image","created":"2025-09-10","cited_by_count":0,"area":null},{"id":"2512.01517","title":"Neural Networks for Predicting Permeability Tensors of 2D Porous Media: Comparison of Convolution- and Transformer-based Architectures","created":"2025-12-01","cited_by_count":0,"area":null},{"id":"2605.25949","title":"Small Models, Strong Priors: Architectural Inductive Bias for Parameter-Efficient Neural PDE Solvers","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2605.31535","title":"RayDer: Scalable Self-Supervised Novel View Synthesis from Real-World Video","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.14757","title":"Spatial Priors via Space Filling Curves for Small and Limited Data Vision Transformers","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2607.18504","title":"Now We Know? A Systematic Comparison of TerraMind and THOR","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2607.19378","title":"Native Multi-Dimensional Subquadratic Operators via Input Dependent Long Convolutions","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2609.37809","title":"Pixel-Level Transformers in Remote Sensing: A Canopy Height Case Study","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}