Welcome to VidLLMs Workshop
Join us at CVPR 2026 for a full-day event exploring the latest in Video Large Language Models. Engage with leading experts, participate in challenge tracks, and discover the future of video understanding.
Key Highlights
- Challenge prizes of $6,000+ at stake
- Travel support for underrepresented groups
- Invited talks and panel discussions
🚨 🚨 🚨 News 🚨 🚨 🚨
- [May 11, 2026] Travel award winners announced, see the Travel Support section for the full winners list.
- [Apr 20, 2026] Paper submission deadline has been extended to April 23, 2026 (11:59 PM Pacific Time).
- [Apr 15, 2026] Accepting challenges submissions on EvalAI.
- [Apr 12, 2026] Travel support applications are now being accepted through April 30, 2026 (11:59 PM Pacific Time). Apply via the travel support registration form.
- [Feb 8, 2026] Paper submissions are now open! Submit your work on OpenReview
- [Dec 22, 2025] Workshop Proposal Accepted by CVPR 2026
Call to Action
About the Workshop
The VidLLMs Workshop focuses on the latest advancements and challenges of Video Large Language Models. We aim to bring together researchers and practitioners from academia and industry to discuss open problems, applications, and future directions in this space.
Topics of Interest
- Methods/Algorithms: Training MLLMs on video with objective/reward design and efficient learning, extended to predictive world-model objectives, VLA perception–language–action loops, and unified backbones that share representations across image–video–audio–text.
- Data Creation: Innovative strategies for leveraging web video data, advanced filtering techniques, synthetic data generation, long video understanding datasets and enriching datasets for video instruction tuning.
- Evaluation and Analysis: Robust evaluation frameworks for existing models, focusing on improving interpretability, deriving novel insights, and introducing new metrics and benchmarks for VidLLMs.
- Best Practices: Reproducible training/eval protocols, including closed-loop rollout training, horizon-aware curricula, and policy/plan logging for unified/VLA systems.
- Applications: From classic CV tasks to simulation and robotics, planning/forecasting with world models, and action-grounded assistants powered by unified VidLLM stacks.
- Comparison and Benchmarking: Systematic studies versus expert CV pipelines and among world-model, VLA, and unified approaches, measuring generalization, data/compute efficiency, and cost.
- Limitations, Risks and Safety: Addressing bias, fairness, and ethical challenges, including factuality, hallucination, and safety concerns in VidLLMs, and action safety and intervention, error compounding in long-horizon rollouts, and modality leakage in unified models.
- Emerging Research Areas: Long-form video understanding and efficient high-resolution video tasks, video grounding LLMs, and fully unified multimodal architectures.
- Vision-Language-Action (VLA): Integrating perception-language-action loops for robotics, simulation, and embodied video reasoning.
- World Models: Learning environment dynamics, future state prediction, and generative modeling of physically consistent reality.
Note: We encourage submissions and discussions on bias, fairness, and ethical considerations. Our workshop is committed to creating an inclusive environment for participants from diverse backgrounds.
Our Sponsors
Travel Support
Partial travel support may be available for participants from underrepresented schools or regions, enabling them to attend CVPR 2026 and participate in the VidLLMs Workshop. Details to be announced.
Eligibility
- Must be from an underrepresented geographic region or school
- Have an accepted paper or top challenge submission
How to Apply
Please fill out this travel support registration form, due April 30, 2026.
Travel Award Winners
| Full Name | Affiliation | Country |
|---|---|---|
| MD AJHARUL ISLAM JOBAER | Rajshahi University of Engineering & Technology | Bangladesh |
| Jyothi Swaroopa Jinka | International Institute of Information Technology Hyderabad (IIITH) | India |
| Javeria Farooq | National University of Computer and Emerging Sciences | Pakistan |
| Merve Tapli | RA | Türkiye |
| Muhamad Iqbal Januadi Putra | Universitas Siber Asia | Indonesia |
| St. Mark Adebayo | Obafemi Awolowo University, Ile-Ife | Nigeria |
| Nestor Rafael Audante Ramos | Universidad Nacional de Ingeniería | Peru |
| Nacef Mbarek | Ecole Polytechnique de Tunisie | Tunisia |
| Cyndi Nayeli Silva Abanto | University of Piura | Peru |
| Mariana Risco Cosavalente | Federal University of Rio Grande do Sul | Brazil |
Organizing Committee
General Chairs
(UCF)
(Amazon & UMD)
(UPenn & Amazon)
(IIIT Hyderabad)
(Univ. of Western Australia)
(Amazon)
(NUS)
(Univ. of Modena & Reggio Emilia)
(Univ. of Amsterdam)
(MBZUAI & Linkoping Univ.)
(Amazon)
(Amazon)
(Amazon)
(Amazon)
(Google)
(Google)
Program Chairs
(Amazon)
(Amazon)
(UCF)
(Amazon)
(Amazon)
Challenge Organizers
(MBZUAI)
(MBZUAI)
(UCF)
(UCF)
(University of Tübingen)
Registration
To attend the VidLLMs Workshop, register through the main CVPR 2026 registration page (available closer to the event). Select the "VidLLMs Workshop" add-on. Early-bird and regular registration fees apply.
For more information, please visit the CVPR 2026 official website or contact us directly if you have questions about workshop fees and logistics.
Contact Us
For general inquiries about submissions, challenges, or logistics:
- Email: vidllmsworkshop@gmail.com