{"total":16,"rows":[{"id":"2508.15281","title":"MMQ: Multimodal Mixture-of-Quantization Tokenization for Semantic ID Generation and User Behavioral Adaptation","created":"2025-08-21","cited_by_count":10,"area":null},{"id":"2603.18660","title":"Multimodal Model for Computational Pathology:Representation Learning and Image Compression","created":"2026-03-19","cited_by_count":6,"area":null},{"id":"2512.00450","title":"RecruitView: A Multimodal Dataset for Predicting Personality and Interview Performance for Human Resources Applications","created":"2025-11-29","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":"2603.01547","title":"PathMoE: Interpretable Multimodal Interaction Experts for Pediatric Brain Tumor Classification","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2603.03564","title":"Modeling Cross-vision Synergy for Unified Large Vision Model","created":"2026-03-03","cited_by_count":1,"area":null},{"id":"2603.13326","title":"Feature-level Interaction Explanations in Multimodal Transformers","created":"2026-03-04","cited_by_count":1,"area":null},{"id":"2604.10695","title":"Retrieving to Recover: Towards Incomplete Audio-Visual Question Answering via Semantic-consistent Purification","created":"2026-04-12","cited_by_count":1,"area":null},{"id":"2607.00573","title":"BrainFIBRE: A Foundation Model via Information Decomposition for Brain Microstructure","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2604.09288","title":"Are Independently Estimated View Uncertainties Comparable? Unified Routing for Trusted Multi-View Classification","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2605.08585","title":"PromptDx: Differentiable Prompt Tuning for Multimodal In-Context Alzheimer's Diagnosis","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2606.09853","title":"SynIB: Informational Bottleneck for Maximizing Synergy in Multimodal Learning","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2608.07867","title":"CONFER: Conflict-Aware Evidence Negotiation for Regime-Calibrated Weak Supervision in Multimodal Emotion Recognition","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2608.08148","title":"DoGMA: A Central-Dogma-Guided Foundation Model for Multi-Omics Alignment and Multi-Task Learning in Oncology","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2609.28836","title":"M$^2$PFN: End-to-End Disentangled Alignment for Generalizable Multimodal In-Context Learning in Alzheimer's Disease","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.39456","title":"Mutual Equilibrium: Multimodal Representation Learning through Reciprocal Feedback","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}