NeuroMM 2026

News

Latest updates for the workshop and challenge.

March 7, 2026 The NeuroMM 2026 Grand Challenge received official approval from ACM Multimedia 2026.
March 11, 2026 The NeuroMM 2026 Workshop was officially accepted for inclusion in ACM Multimedia 2026.
March 21, 2026 The official website of NeuroMM 2026 was launched.

About the Workshop

Multimedia research has traditionally focused on external perception modalities such as images, video, audio, and language. In contrast, neurophysiological signals, including electroencephalography (EEG), electrocardiography (ECG), electromyography (EMG), and wearable biosensors, encode internal human states related to cognition, attention, emotion, and neural dynamics.

NeuroMM 2026 bridges this divide by introducing Multimodal Neurophysiological Intelligence, a unified computational framework that synergizes heterogeneous physiological signals with synchronized multimedia streams. This approach treats physiological sensing not as a niche medical modality, but as a core extension of multimedia computing for joint reasoning over internal and external human states.

Unlike traditional biomedical workshops, NeuroMM centers on multimedia-driven neurophysiological reasoning. Beyond our core focus on epilepsy detection, we aim to establish an ongoing ecosystem covering seizure prediction, mental health assessment, sleep analysis, and cardiac monitoring, providing shared tasks, datasets, and evaluation protocols for trustworthy multimodal neuro-intelligence.

Call for Papers (CFP)

We invite original submissions on multimodal neurophysiological intelligence for human-aware multimedia.

We invite researchers and practitioners to submit original papers aligned with the workshop's theme. Submissions can include methodological advancements, system designs, new benchmark datasets, and clinical applications.

Topics of Interest

Foundations & Core Methodologies

Cross-modal alignment and reasoning between physiological signals (EEG, ECG, EMG) and multimedia (video/audio/text)
Neuro-signal foundation models and large multimodal models (LMMs) for physiological data
Robust learning addressing noise, missing modalities, hallucination, and uncertainty in multimodal understanding
Self-supervised and representation learning for multi-channel neurophysiological signals

Applications & Systems

Clinical and healthcare neuro-multimedia applications (e.g., epilepsy detection, mental health, sleep analysis)
Emotion recognition in conversation, attention, and cognitive state modeling via joint internal-external sensing
Human-centered AI, affective computing, and neuro-aware multimedia understanding
Real-time processing and edge computing for wearable neuro-multimedia systems

Data, Evaluation & Ethics

Dataset construction, open-source benchmarks, and evaluation protocols for neuro-multimedia
Trustworthy AI: Explainability, bias mitigation, and ethics in physiological data processing
Privacy-preserving machine learning and federated learning for sensitive neuro-signals

Submission Guidelines

Paper Format: Submissions must follow the official ACM Multimedia 2026 formatting guidelines.
Submission Portal: [Link to CMT/OpenReview will be updated here]
All accepted papers will be included in the ACM Multimedia 2026 Workshop Proceedings.
Presentation Policy (ACM MM 2026): ACM Multimedia 2026 is an on-site event only. All papers and contributions must be presented physically on-site. Remote presentations are not allowed. Papers/contributions not presented on-site will be treated as no-show and removed from the conference proceedings.
Open Access Policy: ACM has started the Open Access publishing model. Please check the official ACM MM 2026 policy and details here: https://2026.acmmm.org/site/calls-dates.html.

NeuroMM Grand Challenge

Interictal Epileptiform Discharge Detection and Localization in Multimodal Neuro-Signals

Challenge Overview

NeuroMM 2026 reframes epilepsy analysis as multimodal reasoning by integrating EEG-centered physiological data with synchronized contextual information. The challenge is built on vEpiSet, a clinically grounded benchmark collected under standardized protocols at Peking Union Medical College Hospital.

Dataset Highlights: 84 subjects (52 epilepsy, 32 control), 20-minute recordings per subject, and 25,449 four-second epochs with expert-reviewed labels.

Official Tracks

NMM-Basic-IED: Robust IED detection from heterogeneous physiological signals.
NMM-Context-IED: Vision-enhanced detection with synchronized contextual features.
NMM-Source-IED: Spatial localization of epileptogenic regions across five classes.

View Full Challenge Details