GreenMM: Efficient Systems and AI for the Planet
Workshop at ACM Multimedia 2026 (ACM MM 2026), Rio de Janeiro, Brazil

GreenMM brings together researchers working on efficient multimedia AI systems and multimedia AI for environmental and planetary applications. The workshop focuses on building multimedia models that are both technically strong and environmentally responsible. Multimedia AI spans vision, video, audio, language, and multimodal learning. It is now one of the most computationally demanding areas of AI, while also becoming central to biodiversity monitoring, climate analysis, environmental sensing, agriculture, and disaster response.

Topics of interest include, but are not limited to:

Efficient and Sustainable Multimedia AI Systems
- Energy and memory efficient video and multimodal architectures
- Efficient vision language and multimodal foundation models
- Compression, pruning, quantization, and distillation for multimedia
- Sparse, adaptive, and token reduction methods for vision and video
- Parameter efficient fine tuning for large multimodal models
- Efficient generative models for image, audio, and video
- Carbon aware training, scheduling, and deployment
- Resource efficient inference for edge and real time systems
- Data efficient learning under limited annotations
- Benchmarking and reporting of energy and carbon footprint

Multimedia AI for Environmental and Planetary Applications
- Vision and video analysis for biodiversity and wildlife monitoring
- Acoustic and audio based monitoring of ecosystems and species
- Satellite and aerial imagery analysis for land use and climate change
- Environmental change detection in long term multimodal streams
- AI for precision agriculture and sustainable food systems
- Multimedia sensing for water, air, and soil quality
- Disaster monitoring and climate risk analysis
- Vision language models for environmental reporting
- Low cost, scalable sensing systems for environmental monitoring
- Integration of video, audio, satellite, and text data

Submission Format
Prospective authors are invited to submit high quality full papers representing original results. Submissions will follow the ACM MM 2026 format and must adhere to the main conference submission style, format, length restrictions, and camera ready timeline.

Submission link: https://openreview.net/group?id=acmmm.org/ACMMM/2026/Workshop/GreenMM

Workshop website: https://sites.google.com/view/greenmm-workshop/home