paper-with-me

Papers

MIMIC: Multimodal Inversion for Model Interpretation and Conceptualization

2025-08-11 · Animesh Jain, Alexandros Stergiou arxiv

Vision Language Models (VLMs) encode multimodal inputs over large, complex, and difficult-to-interpret architectures, which limit transparency and trust. We propose a Multimodal Inversion for Model Interpretation and Conceptualization (MIMIC) framework that inverts the internal encodings of VLMs. MIMIC uses a joint VLM-based inversion and a feature alignment objective to account for VLM's autoregressive processing. It additionally includes a triplet of regularizers for spatial alignment, natural image smoothness, and semantic realism. We evaluate MIMIC both quantitatively and qualitatively by inverting visual concepts across a range of free-form VLM outputs of varying length. Reported results include both standard visual quality metrics and semantic text-based metrics. To the best of our knowledge, this is the first model inversion approach addressing visual interpretations of VLM concepts.

📄 PDF Abstract BibTeX arXiv:2508.07833

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

MEETI: A Multimodal ECG Dataset from MIMIC-IV-ECG with Signals, Images, Features and Interpretations

2025-07-21 · Deyun Zhang, Xiang Lan, Shijia Geng, Qinghao Zhao 외 arxiv

Electrocardiogram (ECG) plays a foundational role in modern cardiovascular care, enabling non-invasive diagnosis of arrhythmias, myocardial ischemia, and conduction disorders. While machine learning has achieved expert-l…

EchoVLM: Measurement-Grounded Multimodal Learning for Echocardiography

2025-12-13 · Yuheng Li, Yue Zhang, Abdoul Aziz Amadou, Yuxiang Lai 외 arxiv

Echocardiography is the most widely used imaging modality in cardiology, yet its interpretation remains labor-intensive and inherently multimodal, requiring view recognition, quantitative measurements, qualitative assess…

Text Retrieval

XAI for In-hospital Mortality Prediction via Multimodal ICU Data

2023-12-29 · Xingqiao Li, Jindong Gu, Zhiyong Wang, Yancheng Yuan 외

Predicting in-hospital mortality for intensive care unit (ICU) patients is key to final clinical outcomes. AI has shown advantaged accuracy but suffers from the lack of explainability. To address this issue, this paper p…

Decision MakingMortality Prediction

Rethinking Model Inversion Attacks With Patch-Wise Reconstruction

2023-12-12 · Jonggyu Jang, Hyeonsu Lyu, Hyun Jong Yang

Model inversion (MI) attacks aim to infer or reconstruct the training dataset through reverse-engineering from the target model's weights. Recently, significant advancements in generative models have enabled MI attacks t…

Generative Adversarial Network

Towards geological inference with process-based and deep generative modeling, part 2: inversion of fluvial deposits and latent-space disentanglement

2025-10-20 · Guillaume Rongier, Luk Peeters arxiv

High costs and uncertainties make subsurface decision-making challenging, as acquiring new data is rarely scalable. Embedding geological knowledge directly into predictive models offers a valuable alternative. A joint ap…