{"total":13,"rows":[{"id":"2404.04125","title":"No \"Zero-Shot\" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance","created":"2024-04-04","cited_by_count":75,"area":null},{"id":"2402.02968","title":"Delving into Multi-modal Multi-task Foundation Models for Road Scene Understanding: From Learning Paradigm Perspectives","created":"2024-02-05","cited_by_count":23,"area":null},{"id":"2509.25172","title":"Personalized Vision via Visual In-Context Learning","created":"2025-09-29","cited_by_count":14,"area":null},{"id":"2412.16156","title":"Personalized Representation from Personalized Generation","created":"2024-12-20","cited_by_count":9,"area":null},{"id":"2510.20860","title":"Data-Centric Lessons To Improve Speech-Language Pretraining","created":"2025-10-22","cited_by_count":3,"area":null},{"id":"2601.14894","title":"To Neuro-Symbolic Classification and Beyond by Compiling Description Logic Ontologies to Probabilistic Circuits","created":"2026-01-21","cited_by_count":3,"area":null},{"id":"2403.04125","title":"ComFe: An Interpretable Head for Vision Transformers","created":"2024-03-07","cited_by_count":2,"area":null},{"id":"2605.28563","title":"A Multi-dimensional Framework for Evaluating Generalization in EEG Foundation Models","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2505.13099","title":"Industrial Synthetic Segment Pre-training","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2506.16821","title":"Self-supervised Feature Extraction for Enhanced Ball Detection on Soccer Robots","created":"2025-06-20","cited_by_count":0,"area":null},{"id":"2507.18517","title":"Object segmentation in the wild with foundation models: application to vision assisted neuro-prostheses for upper limbs","created":"2025-07-24","cited_by_count":0,"area":null},{"id":"2512.06006","title":"Simple Agents Outperform Experts in Biomedical Imaging Workflow Optimization","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2606.03837","title":"Where Do We (Not) Need Temporal Context in Low-Resource Video Task Adaptation?","created":"2026-06-02","cited_by_count":0,"area":null}],"next_cursor":null}