Submission deadline: March 21, 2025 (11:59 PM Pacific Time)
Review ends: March 28, 2025
Notification of acceptance: March 31, 2025
Camera-ready submission: April 10, 2025
The workshop targets computational efficiency of training, adaptation, and inference for large vision models including but not limited to:
Scalable architectures
Long context modeling by developing state space models e.g., Mamba, and recurrent models e.g., RWKV, GLA and xLSTM, for computer vision
Scaling up model parameters by mixture of experts architectures e.g., sparse MoE for computer vision
Optimizing vision transformers e.g., token merging and pruning, and approximated self-attention
Efficiency of generative models
Efficient architectures e.g., hierarchical diffusion transformers (DiTs), scalable pixel-space diffusion models, and efficient auto-regressive models
Fast diffusion sampling e.g., adversarial distillation, and consistency models
Efficient autoregressive models for generating images and videos, e.g., parallel decoding, speculative decoding, and KV caching for vision models
Efficient generation of high-resolution images and videos
Efficient generation of 3D objects and scenes e.g., by diffusion models, Gaussian splatting, and NeRF
Efficient generation of vision language models e.g. multi-modal LLMs
Efficiency of foundation vision models
Efficient foundation models for perception e.g., open set object detection, semantic segmentation and depth estimation
Efficient foundation models for representation learning e.g., DINO and CLIP
Compression, quantization, conditional compute, pruning and distillation of LVMs
Deploying LVMs on low power devices e.g., smartphone
Submission link: https://cmt3.research.microsoft.com/ELVM2025
Format: We accept two forms of papers:
Short paper: short papers should not exceed 4 pages (excluding references). Short papers are intended to share exciting and novel early stage ideas. A short paper should describe ideas and have preliminary experiments to support the ideas, although extensive comparisons and analyses are not needed.
Long paper: Long papers should not exceed 8 pages (excluding references). Long papers are intended to present mature works, not only describing novel ideas but also have sufficient experiments and comparisons to support the proposed ideas.
All papers need to be formatted as per the CVPR 2025 guidelines. Please use the template made available at CVPR2025AuthorGuidelines. Papers beyond 8 pages in length (excluding references) will be desk rejected.
Publication: All long accepted papers will be published as part of the CVPR'25 workshop proceedings.
Please feel free to post your questions to habibian.a.h@gmail.com.