{"total":15,"rows":[{"id":"2112.04446","title":"Everything at Once -- Multi-modal Fusion Transformer for Video Retrieval","created":"2021-12-08","cited_by_count":79,"area":null},{"id":"2104.02862","title":"Farewell to Mutual Information: Variational Distillation for Cross-Modal Person Re-Identification","created":"2021-04-07","cited_by_count":50,"area":null},{"id":"2210.17444","title":"Multimodal Information Bottleneck: Learning Minimal Sufficient Unimodal and Multimodal Representations","created":"2022-10-31","cited_by_count":48,"area":null},{"id":"2308.13077","title":"Preserving Modality Structure Improves Multi-Modal Learning","created":"2023-08-24","cited_by_count":13,"area":null},{"id":"2408.08074","title":"A Survey on Integrated Sensing, Communication, and Computation","created":"2024-08-15","cited_by_count":12,"area":null},{"id":"2412.18277","title":"Towards Modality Generalization: A Benchmark and Prospective Analysis","created":"2024-12-24","cited_by_count":10,"area":null},{"id":"2106.15550","title":"Unified Questioner Transformer for Descriptive Question Generation in Goal-Oriented Visual Dialogue","created":"2021-06-29","cited_by_count":8,"area":null},{"id":"2411.12126","title":"MMBind: Unleashing the Potential of Distributed and Heterogeneous Data for Multimodal Learning in IoT","created":"2024-11-18","cited_by_count":6,"area":null},{"id":"2112.13985","title":"LatteGAN: Visually Guided Language Attention for Multi-Turn Text-Conditioned Image Manipulation","created":"2021-12-28","cited_by_count":5,"area":null},{"id":"2505.15217","title":"Multimodal Conditional Information Bottleneck for Generalizable AI-Generated Image Detection","created":"2025-05-21","cited_by_count":5,"area":null},{"id":"2505.21524","title":"Learning Shared Representations from Unpaired Data","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2206.09548","title":"Variational Distillation for Multi-View Learning","created":"2022-06-20","cited_by_count":3,"area":null},{"id":"2207.08001","title":"SVGraph: Learning Semantic Graphs from Instructional Videos","created":"2022-07-16","cited_by_count":2,"area":null},{"id":"2510.03639","title":"Towards Unsupervised Speech Recognition at the Syllable-Level","created":"2025-10-04","cited_by_count":2,"area":null},{"id":"2509.21711","title":"Multi-modal Bayesian Neural Network Surrogates with Conjugate Last-Layer Estimation","created":"2025-09-26","cited_by_count":0,"area":null}],"next_cursor":null}