Multimodal Model Interpretability

Follow this topic Ask about this topic

Momentum

11 papers in the last four weeks, up 267% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 70

All topics

Attending to Multimodal Generation One Token at a Time
Jul 4, 2026Varun Gupta, Vineet Gandhi, Makarand TapaswiMultimodal Large Language Models Multimodal Generation
CVIT, IIIT Hyderabad
See the Emotion: A Facial Emoji Proxy Modeling for EEG Emotion Recognition
Jul 3, 2026Jingjing Hu, Guo Dan, Haofan Cheng +4Multimodal Model Interpretability EEG Emotion Recognition
Hefei University of Technology · Institute of Artificial Intelligence, Hefei Comprehensive National Science Center · The Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology +3
CALM: Interpretable Cross-Modal Alignment for Biomarker Discovery from Unpaired Data
Jul 2, 2026Jueqi Wang, Zachary Jacokes, John Darrell Van Horn +3Cross-Modal Alignment Scientific Discovery
Department of Electrical and Computer Engineering, Boston University · School of Data Science, University of Virginia · Department of Psychology, University of Virginia +2
MultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answering
Jul 1, 2026Dang Quang Thien Tran, Quang V. Dang, Vinamra Tyagi +7Multimodal QA Document QA
University of Massachusetts, Amherst · 2Adobe Research, San Jose
FedLAB: Traceable Semantic Codebooks for Federated Multimodal Graph Foundation Learning
Jun 30, 2026Zekai Chen, Kairui Yang, Xuaner Chen +4Multimodal Federated Learning Representation Learning
Beijing Institute of Technology, Beijing, China
Forewarned is Forearmed: When Non-Sequential Embedding Turns Into an Anomaly Detector
Jun 29, 2026Elys Allesiardo, Antoine Caubrière, Valentin VielzeufMultimodal Embedding Multimodal Model Interpretability
Orange Research 4 Rue du Clos Courtel, 35510 Cesson-Sévigné, France
Traffic-CBM: A Structurally Interpretable Multimodal Framework for Encrypted Traffic Classification
Jun 29, 2026Honglei Jin, Wenshuo Chen, Shaofeng Liang +6Encrypted Network Traffic Analysis Multimodal Classification
HKUST (GZ) Guangzhou, China · Shandong University Qingdao, China
Does Role Specialization Matter for Explanation Faithfulness in Mixture-of-Experts?
Jun 28, 2026Yeji Kim, Housam Babiker, Mi-Young Kim +1Multimodal Model Interpretability Mixture-of-Experts Models
University of Alberta, Edmonton, AB, Canada · University of Waikato, Hamilton, New Zealand · University of Alberta, Camrose, AB, Canada
Enhancing Clinician Decision-Making via Uncertainty-Aware Multi-Expert Fusion for Stroke Rehabilitation
Jun 23, 2026Tamim Ahmed, Thanassis RikakisClinical Decision-Making Multimodal Model Interpretability
Bioemdical Engineering, University of Soutehrn California,, Los Angeles, 90007, CA, USA.
Cohort-Anchored Foundation Models for Electronic Health Records: From Risk Scores to Auditable Peer Cohorts
Jun 20, 2026Kaiping ZhengClinical Decision-Making Multimodal Model Interpretability
National University of Singapore
Multimodal Concept Bottleneck Models
Jun 18, 2026Tongqing Shi, Ge Yan, Tuomas Oikarinen +1Concept Bottleneck Models VLM Interpretability
UC San Diego
An approach with Visual and Tabular Mamba to multimodal medical data using Mixed Fusion
Jun 17, 2026Matheus B. Rocha, Gustavo B. Dettogni, Renato A. KrohlingMamba Multimodal Classification
Labcin - Nature Inspired Computing Lab, Federal University of Espírito Santo, Vitória, Brazil · PPGI - Graduate Program in Computer Science, Federal University of Espírito Santo, Vitória, Brazil
ThinkDeception: A Progressive Reinforcement Learning Framework for Interpretable Multimodal Deception Detection
Jun 17, 2026Jinhao Song, Shan Liang, Yiqun Yue +2RL for Language Model Reasoning Multimodal Large Language Models
Xi’an Jiaotong-Liverpool University · Suzhou, China
SAE++: Cascaded Sparse Autoencoders Learn Multi-Level Visual Concepts in Multimodal LLMs
Jun 15, 2026Yusong Zhao, Hengyi Wang, Tanuja Ganu +2Hierarchical Representation Learning Multimodal Large Language Models
Rutgers University. · Microsoft.
DifFRACT: Diffusion Feature Reconstruction and Attribution for Circuit Tracing
Jun 14, 2026Artyom Mazur, Nina Konovalova, Aibek AlanovDiffusion Transformer Multimodal Model Interpretability
HSE University · AXXX
DeceptionX: Explainable Deception Detection with Multimodal Large Language Models
Jun 9, 2026Jiayu Zhang, Shuo Ye, Jiajian Huang +7Multimodal Large Language Models Multimodal Reasoning
Great Bay University Dongguan, Guangdong, China · Hong Kong Polytechnic University HongKong, China
From Senses to Decisions: The Information Flow of Auditory and Visual Perception in Multimodal LLMs
Jun 8, 2026Wish Suharitdamrong, Muhammad Awais, Xiatian Zhu +1Efficient Multimodal Inference Multimodal Large Language Models
Surrey Institute for People-Centred AI (PAI), University of Surrey, UK · Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK
Disentangling Hallucinations: Orthogonal Semantic Projection for Robust Interpretability
Jun 8, 2026Emirhan Bilgiç, Baptiste Caramiaux, Zhi Yan +1VLM Interpretability Multimodal Model Interpretability
U2IS, ENSTA, Institut Polytechnique de Paris, Palaiseau · ISIR, Université Sorbonne, Pierre et Marie Curie, Paris · AMIAD, Pôle Recherche, Palaiseau
When Correct Decisions Hide Internal Stress: Decision-State Probing in Multimodal Language Models
Jun 7, 2026Haoran Zhao, Soyeon Caren Han, Eduard HovyMultimodal Robustness Multimodal Large Language Models
1The University of Melbourne
GridVQA-X: A Framework for Evaluating Multimodal Explainability Methods
Jun 2, 2026Sujay Belsare, Sudarshan Nikhil, Sushant Kumar +2Multimodal Reasoning Multimodal Model Interpretability
1IIIT Hyderabad, India · University of Virginia, USA
Towards Understanding Modality Interaction in Multimodal Language Models via Partial Information Decomposition
May 31, 2026Wanlong Fang, Tianle Zhang, Wen Tao +1Multimodal Grounding Multimodal Large Language Models
College of Computing and Data Science, Nanyang Technological University, Singapore · Lee Kong Chian School of Medicine, Nanyang Technological University, Singapore · Centre of AI in Medicine (C-AIM), Nanyang Technological University, Singapore
MLLM-Microscope: Unlocking Hidden Structure Within Multimodal Large Language Models
May 30, 2026Ravil Mussabayev, Rustam MussabayevRepresentation Geometry Multimodal Large Language Models
Satbayev University
ConceptM $^3$ oE: Concept-Guided Multimodal Mixture of Experts for Interpretable Computational Pathology
May 23, 2026Xuan Wang, Zhongling Xu, Gopi Kannedhara +13Computational Pathology Concept Bottleneck Models
University of Texas at Austin, Austin, TX, USA · University of North Carolina at Chapel Hill, NC, USA · Dell Children’s Medical Center, Austin, TX, USA +2
Transcoders Trace Visual Grounding and Hallucinations in Vision-Language Models
May 21, 2026Dimitrios Damianos, Leon Voukoutis, Georgios Skyrianos +2Object Hallucination in VLMs VLM Interpretability
Institute of Language and Speech Processing, Athena Research Center Athens, Greece
Measuring Cross-Modal Synergy: A Benchmark for VLM Explainability
May 21, 2026Joël Roman Ky, Salah Ghamizi, Maxime CordyVLM Interpretability Shapley Value Attribution
University of Luxembourg, Luxembourg · Luxembourg Institute of Health (LIH), Luxembourg
ProtoMedAgent: Multimodal Clinical Interpretability via Privacy-Aware Agentic Workflows
May 13, 2026Alvaro Lopez Pellicer, Plamen Angelov, Marwan Bukhari +3LLM Hallucination Mitigation Healthcare
School of Computing and Communications, Lancaster University · Lancaster Medical School, Lancaster University · PUC-Rio, Puc-Behring Institute for AI
Supervised Deep Multimodal Matrix Factorization for Interpretable Brain Network Analysis
May 13, 2026Amjad Seyedi, Lifang He, Songlin Zhao +2Neural Network Interpretability Multimodal Graph Learning
Dept. of Mathematics & Operational Research University of Mons, Mons, Belgium · Dept. of Computer Science & Engineering Lehigh University, Bethlehem, PA, USA · Dept. of Industrial & Systems Engineering Lehigh University, Bethlehem, PA, USA
Probing Cross-modal Information Hubs in Audio-Visual LLMs
May 11, 2026Jihoo Jung, Chaeyoung Jung, Ji-Hoon Kim +1Cross-Modal Learning Multimodal Large Language Models
Department of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea · The Graduate School of Advanced Imaging Science, Multimedia & Film, Chung-Ang University, Seoul, Republic of Korea
The Metagame of Interpretability and Meta-Attributions
May 7, 2026Hubert Baniecki, Przemyslaw Biecek, Fabian FumagalliTransformer Interpretability Feature Interaction Modeling
University of Warsaw · Centre for Credible AI, Warsaw University of Technology · Bielefeld University +1
Gated Multimodal Learning for Interpretable Property Energy Performance Prediction and Retrofit Scenario Analysis
May 6, 2026Yunfei Bai, Aaron Tesfa Tsion, Raul Rosales +2Multimodal Model Interpretability Multimodal Fusion
Department of Engineering, King’s College London London, UK

Jul 4, 2026, cs.CVJ/K move · Enter open · S save

Attending to Multimodal Generation One Token at a Time

Varun Gupta, Vineet Gandhi, Makarand Tapaswi

CVIT, IIIT Hyderabad

Multimodal Large Language Models Multimodal Generation Multimodal Foundation Models Multimodal Model Interpretability Multimodal Understanding

Open paper AskPDF arXiv

Multimodal large language models (MLLMs) generate responses autoregressively, integrating visual and linguistic information in an evolving context. Prior work on interpretability has focused on individual layers and circuits (where), leaving the token-level dynamics of multimodal computation during generation (when) underexplored. We address this gap and study attention shifts as per semantic role; tracking model attention to image, text, instruction, and previously generated tokens, One Token at a Time (OTaT). We introduce multimodal tasks that require explicit switching between visual and textual context within a single response. Across two mainstream model families and four open-weight MLLMs of varying sizes, we establish consistent patterns: attention to image peaks at tokens requiring image-derived information, instruction tokens are revisited during task transitions, and attention to previously generated tokens increases as the generation progresses. Causal attention blocking interventions validate the functional role of these trends. We profile model behavior under disrupted attention and observe responses falling back to language priors, or exhibiting cross-modal leakage, denial, or recovery. Finally, informed of the attention dynamics through our novel analysis, we propose a simple test-time intervention to boost attention to the relevant modality at the right time, significantly improving multimodal task performance.

Momentum

Related topics

Latest papers 70