VLA-Medical-Theranostics1: Vision-Language and Agentic AI Modeling in Image-guided Theranostics International Convention & Exhibition Centre Sydney, Australia, December 1, 2026 |
| Conference web page | https://sites.google.com/view/vla-medical-theranostics/ |
| Submission link | https://easychair.org/conferences/?conf=vlamedicaltheranosti0 |
| Abstract registration deadline | November 12, 2026 |
| Submission deadline | November 16, 2026 |
VLA Medical Theranostics
The workshop Vision-Language and Agentic AI Modeling in Image-Guided Theranostics will be held as part of International Conference on Digital Image Computing: Techniques and Applications (DICTA) by December 1, 2026 in Sydney, Australia. The workshop will bring together researchers, engineers, clinicians, and industry experts working across computer vision, medical image analysis, multimodal learning, foundation models, vision-language modelling, agentic AI, medical robotics, digital healthcare, and clinical decision support.
The workshop will explore how emerging intelligent systems can move beyond isolated task-specific models toward integrated systems capable of understanding complex medical scenes, combining heterogeneous imaging and clinical information, supporting human–AI interaction, and assisting diagnosis, treatment planning, image-guided intervention, and outcome evaluation.
Particular emphasis will be placed on the development of safe, reliable, and clinically deployable intelligent medical systems, as well as the challenges involved in translating vision-language, multimodal, and agentic AI technologies from methodological development toward real-world clinical use.
Submission Guidelines
VLA Medical Theranostics is a non-archival workshop. We welcome original, emerging, recently published, accepted, or submitted research relevant to the workshop themes, provided that authors comply with the publication and presentation policies of the venue where the work has previously been submitted or published.
Submissions should normally be 2–4 pages and may present early-stage or completed research, technical studies, benchmark proposals, system demonstrations, methodological developments, or clinical and translational perspectives.
The following contribution categories are welcome:
Extended abstracts / short papers describing original or emerging research in vision-language modelling, multimodal AI, foundation models, agentic AI, image-guided intervention, medical image analysis, clinical decision support, medical robotics, and related areas. Submissions may report completed studies, work in progress, methodological contributions, benchmark or dataset proposals, system integration, or translational investigations.
Lightning-talk and poster contributions describing early-stage research, recently completed work, technical demonstrations, clinical perspectives, preliminary findings, or recently published results that are suitable for discussion with the workshop community. Selected submissions will be presented through a short lightning talk followed by an interactive poster or demonstration session.
Submissions will be reviewed by members of the Program Committee. The review process will emphasise constructive feedback and will consider:
Relevance to the workshop themes
Novelty and technical quality
Clarity of presentation
Contribution to image computing and AI in medicine
Clinical or translational significance
Potential to stimulate interdisciplinary discussion
Accepted contributions will be featured on the workshop website and invited for presentation during the workshop.
List of Topics
Topics of interest include, but are not limited to:
Vision-language and large-language modelling for image-guided medical interventions
Multimodal foundation models for medical imaging and healthcare
Agentic AI for diagnosis, treatment planning, and clinical decision support
Retrieval-augmented generation and knowledge-enhanced medical AI
Generative AI for image-guided diagnosis and therapy
Foundation models for medical image-guided robotics
Multimodal learning for endoscopy, bronchoscopy, endovascular, and intraluminal procedures
Anatomical structure segmentation and recognition
Surgical and interventional scene parsing
Semantic mapping and structured scene understanding
Procedural phase, workflow, and action recognition
Image-guided navigation and intelligent intervention
Depth estimation, 3D reconstruction, and spatial reasoning
Multimodal perception and sensor fusion
Human–AI collaboration in image-guided procedures
Shared autonomy and intelligent robotic assistance
Clinical decision support using multimodal AI
Skill assessment, intent recognition, and operator modelling
AI-assisted screening, diagnosis, and treatment optimisation
Dataset curation, benchmarking, and evaluation protocols
Trustworthy, explainable, and reliable medical AI
Safety and validation of agentic healthcare systems
Clinical translation and deployment of intelligent medical systems
Regulatory and implementation considerations for medical AI
Bench-to-bed development of intelligent healthcare technologies
Organizing Committees
Dr Olatunji Omisore, CQUniversity Australia — Lead Organizer
Dr Jie (Jack) Yang, University of Wollongong — Co-organizer and Panel Moderator
Dr Anwaar Ul-Haq, CQUniversity Australia — Co-organizer
Invited Speakers
The invited speaker programme is being finalised. Current speakers and experts include:
Professor Arcot Sowmya, School of Computer Science and Engineering, UNSW Sydney — Keynote Speaker and Panelist.
Associate Professor Susann Beier, Sydney Vascular Modelling Group, UNSW Sydney — Keynote Speaker.
Associate Professor Ruwan Tennakoon, School of Computing Technologies, RMIT — Keynote Speaker.
Dr David Waddington, Image X Institute, University of Sydney — Keynote Speaker and Panelist.
Dr Rahman Mamunur, Australian Institute of Health Innovation, Macquarie University — Spotlight Speaker.
Dr Eswararaj Sivaraj, Menzies Institute for Medical Research, University of Tasmania — Spotlight Speaker.
Dr. Ziba Gandomakar, Chief Scientific Officer, DetectED-X / Senior Lecturer, University of Sydney — Panelist.
Dr. Shen Lu, Investor Manager (Emerging Tech.), AWS & Firemark Ventures — Panelist.
Additional invited keynote and industry speakers will be announced as confirmations are received.
Publication
VLA-Medical-Theranostics1 is planned as a non-archival workshop. Accepted submissions will not constitute a formal archival proceedings publication unless otherwise announced by the DICTA 2026 organisers.
Accepted contributions may be made available through the workshop website for discussion and presentation purposes. Authors may therefore submit relevant recent work that has already been published, accepted, or submitted elsewhere, subject to the policies of the original publication venue.
Venue
The workshop will be held as part of DICTA 2026 — the International Conference on Digital Image Computing: Techniques and Applications, in Sydney, Australia, on Tuesday, 1 December 2026.
The workshop is planned as a half-day event. A limited hybrid participation option may also be available, subject to the final arrangements and policies of the DICTA 2026 organising committee.
Contact
All questions about submissions and workshop participation should be emailed to:
Dr Olatunji Omisore
School of Engineering and Technology
CQUniversity Australia
Email: o.omisore@cqu.edu.au
Workshop website: https://sites.google.com/view/vla-medical-theranostics/
