{"total":41,"rows":[{"id":"2401.01646","title":"Prototypical Information Bottlenecking and Disentangling for Multimodal Cancer Survival Prediction","created":"2024-01-03","cited_by_count":41,"area":null},{"id":"2404.09403","title":"Neuro-Inspired Information-Theoretic Hierarchical Perception for Multimodal Learning","created":"2024-04-15","cited_by_count":18,"area":null},{"id":"2505.19996","title":"Learning Optimal Multimodal Information Bottleneck Representations","created":"2025-05-26","cited_by_count":15,"area":null},{"id":"2305.11579","title":"Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment","created":"2023-05-19","cited_by_count":13,"area":null},{"id":"2404.08923","title":"Trustworthy Multimodal Fusion for Sentiment Analysis in Ordinal Sentiment Space","created":"2024-04-13","cited_by_count":8,"area":null},{"id":"2309.12067","title":"Survey of Action Recognition, Spotting and Spatio-Temporal Localization in Soccer -- Current Trends and Research Perspectives","created":"2023-09-21","cited_by_count":7,"area":null},{"id":"2502.18331","title":"BottleHumor: Self-Informed Humor Explanation using the Information Bottleneck Principle","created":"2025-02-22","cited_by_count":6,"area":null},{"id":"2312.11128","title":"Unleashing the Power of CNN and Transformer for Balanced RGB-Event Video Recognition","created":"2023-12-18","cited_by_count":5,"area":null},{"id":"2504.18539","title":"Multi-Task Corrupted Prediction for Learning Robust Audio-Visual Speech Representation","created":"2025-01-23","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":"2404.10904","title":"Multi-Task Multi-Modal Self-Supervised Learning for Facial Expression Recognition","created":"2024-04-16","cited_by_count":4,"area":null},{"id":"2504.01676","title":"Satellite Edge Artificial Intelligence with Large Models: Architectures and Technologies","created":"2025-04-02","cited_by_count":4,"area":null},{"id":"2508.16300","title":"A Multimodal-Multitask Framework with Cross-modal Relation and Hierarchical Interactive Attention for Semantic Comprehension","created":"2025-08-22","cited_by_count":4,"area":null},{"id":"2504.09707","title":"InfoMAE: Pair-Efficient Cross-Modal Alignment for Multimodal Time-Series Sensing Signals","created":"2025-04-13","cited_by_count":3,"area":null},{"id":"2504.12151","title":"Towards Explainable Fusion and Balanced Learning in Multimodal Sentiment Analysis","created":"2025-04-16","cited_by_count":3,"area":null},{"id":"2505.17423","title":"VIBE: Annotation-Free Video-to-Text Information Bottleneck Evaluation for TL;DR","created":"2025-05-23","cited_by_count":3,"area":null},{"id":"2506.20494","title":"Multimodal Representation Learning and Fusion","created":"2025-06-25","cited_by_count":3,"area":null},{"id":"2401.09029","title":"Cross-modality Guidance-aided Multi-modal Learning with Dual Attention for MRI Brain Tumor Grading","created":"2024-01-17","cited_by_count":2,"area":null},{"id":"2406.05036","title":"TimeSieve: Extracting Temporal Dynamics through Information Bottlenecks","created":"2024-06-07","cited_by_count":2,"area":null},{"id":"2508.04999","title":"Disentangling Bias by Modeling Intra- and Inter-modal Causal Attention for Multimodal Sentiment Analysis","created":"2025-08-07","cited_by_count":2,"area":null},{"id":"2509.21805","title":"Towards Minimal Causal Representations for Human Multimodal Language Understanding","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2512.22102","title":"Explainable Multimodal Regression via Information Decomposition","created":"2025-12-26","cited_by_count":2,"area":null},{"id":"2509.04459","title":"Uncertainty-Aware Collaborative System of Large and Small Models for Multimodal Sentiment Analysis","created":"2025-08-27","cited_by_count":1,"area":null},{"id":"2509.08469","title":"Maximally Useful and Minimally Redundant: The Key to Self Supervised Learning for Imbalanced Data","created":"2025-09-10","cited_by_count":1,"area":null},{"id":"2510.04000","title":"Distributed Information Bottleneck Theory for Multi-Modal Task-Aware Semantic Communication","created":"2025-10-05","cited_by_count":1,"area":null},{"id":"2511.01444","title":"Robust Multimodal Sentiment Analysis via Double Information Bottleneck","created":"2025-11-03","cited_by_count":1,"area":null},{"id":"2603.01431","title":"SeaVIS: Sound-Enhanced Association for Online Audio-Visual Instance Segmentation","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2603.02695","title":"Addressing Missing and Noisy Modalities in One Solution: Unified Modality-Quality Framework for Low-quality Multimodal Data","created":"2026-03-03","cited_by_count":1,"area":null},{"id":"2604.18460","title":"Learning Invariant Modality Representation for Robust Multimodal Learning from a Causal Inference Perspective","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2401.02717","title":"Complementary Information Mutual Learning for Multimodality Medical Image Segmentation","created":"2024-01-05","cited_by_count":0,"area":null},{"id":"2505.20306","title":"Multi-Modal Artificial Intelligence of Embryo Grading and Pregnancy Prediction in Assisted Reproductive Technology: A Review","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2508.09145","title":"MoLAN: A Unified Modality-Aware Noise Dynamic Editing Framework for Multimodal Sentiment Analysis","created":"2025-07-31","cited_by_count":0,"area":null},{"id":"2508.10644","title":"Conditional Information Bottleneck for Multimodal Fusion: Overcoming Shortcut Learning in Sarcasm Detection","created":"2025-08-14","cited_by_count":0,"area":null},{"id":"2508.19769","title":"AIM: Adaptive Intra-Network Modulation for Balanced Multimodal Learning","created":"2025-08-27","cited_by_count":0,"area":null},{"id":"2509.20225","title":"Multimodal Representation-disentangled Information Bottleneck for Multimodal Recommendation","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2601.09606","title":"GRCF: Two-Stage Groupwise Ranking and Calibration Framework for Multimodal Sentiment Analysis","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2605.28575","title":"A Conflict-Aware Penalty and Statistical Loss Framework for Balancing Modalities and Enhancing Stability in Multimodal Sentiment Analysis","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2605.29900","title":"OVA-IB: One vs All Information Bottleneck for Multi-Modal Alignment","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2609.05174","title":"SMILE: Self-Explainable Multimodal Information Bottleneck for Medical Diagnosis","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.14469","title":"PRI-Net: A Lightweight Multimodal Framework for 3D UAV Localization","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2609.30470","title":"Reliability-aware Cross-sample Enhancement for Robust Multimodal Sentiment Analysis","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}