{"total":27,"rows":[{"id":"2111.14447","title":"ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic","created":"2021-11-29","cited_by_count":150,"area":null},{"id":"2209.03430","title":"Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions","created":"2022-09-07","cited_by_count":116,"area":null},{"id":"2202.05306","title":"Characterizing and overcoming the greedy nature of learning in multi-modal deep neural networks","created":"2022-02-10","cited_by_count":95,"area":null},{"id":"2308.07686","title":"Boosting Multi-modal Model Performance with Adaptive Gradient Modulation","created":"2023-08-15","cited_by_count":73,"area":null},{"id":"2212.08158","title":"MM-SHAP: A Performance-agnostic Metric for Measuring Multimodal Contributions in Vision and Language Models & Tasks","created":"2022-12-15","cited_by_count":43,"area":null},{"id":"2206.01161","title":"Optimizing Relevance Maps of Vision Transformers Improves Robustness","created":"2022-06-02","cited_by_count":41,"area":null},{"id":"2404.18624","title":"Do Vision & Language Decoders use Images and Text equally? How Self-consistent are their Explanations?","created":"2024-04-29","cited_by_count":24,"area":null},{"id":"2305.12393","title":"Layer Collaboration in the Forward-Forward Algorithm","created":"2023-05-21","cited_by_count":21,"area":null},{"id":"2312.00935","title":"Understanding Unimodal Bias in Multimodal Deep Linear Networks","created":"2023-12-01","cited_by_count":19,"area":null},{"id":"2402.06244","title":"Quantifying and Enhancing Multi-modal Robustness with Modality Preference","created":"2024-02-09","cited_by_count":16,"area":null},{"id":"2412.15828","title":"Measuring Cross-Modal Interactions in Multimodal Models","created":"2024-12-20","cited_by_count":16,"area":null},{"id":"2112.04895","title":"Latent Space Explanation by Intervention","created":"2021-12-09","cited_by_count":13,"area":null},{"id":"2205.00302","title":"SHAPE: An Unified Approach to Evaluate the Contribution and Cooperation of Individual Modalities","created":"2022-04-30","cited_by_count":11,"area":null},{"id":"2306.08306","title":"Towards Balanced Active Learning for Multimodal Classification","created":"2023-06-14","cited_by_count":9,"area":null},{"id":"2306.08889","title":"Dissecting Multimodality in VideoQA Transformer Models by Impairing Modality Fusion","created":"2023-06-15","cited_by_count":8,"area":null},{"id":"2509.23499","title":"Multi-modal Data Spectrum: Multi-modal Datasets are Multi-dimensional","created":"2025-09-27","cited_by_count":3,"area":null},{"id":"2211.04971","title":"Understanding Cross-modal Interactions in V&L Models that Generate Scene Descriptions","created":"2022-11-09","cited_by_count":2,"area":null},{"id":"2405.04671","title":"Interpretable Tensor Fusion","created":"2024-05-07","cited_by_count":2,"area":null},{"id":"2503.01904","title":"What are You Looking at? Modality Contribution in Multimodal Medical Deep Learning","created":"2025-02-28","cited_by_count":2,"area":null},{"id":"2509.20641","title":"Investigating Modality Contribution in Audio LLMs for Music","created":"2025-09-25","cited_by_count":2,"area":null},{"id":"2404.18976","title":"Foundations of Multisensory Artificial Intelligence","created":"2024-04-29","cited_by_count":1,"area":null},{"id":"2511.19470","title":"Quantifying Modality Contributions via Disentangling Multimodal Representations","created":"2025-11-22","cited_by_count":1,"area":null},{"id":"2605.18791","title":"SpecX: A Large-Scale Benchmark for Multi-Modal Spectroscopy and Cross-Paradigm Evaluation","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2210.01191","title":"Extending Compositional Attention Networks for Social Reasoning in Videos","created":"2022-10-03","cited_by_count":0,"area":null},{"id":"2309.12463","title":"Impact of architecture on robustness and interpretability of multispectral deep neural networks","created":"2023-09-21","cited_by_count":0,"area":null},{"id":"2608.09276","title":"Verifiably grounded machine interpretation of lunar geology","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.27901","title":"All modalities are equal, but video is more equal: Closing the Cross-Attention Gap in Joint Video Generation","created":"2026-09-23","cited_by_count":0,"area":null}],"next_cursor":null}