CVPR 2024
First Workshop on Efficient and On-Device Generation (EDGE)

Overview and Call for Papers


The First Workshop on Efficient and On-Device Generation (EDGE) at CVPR 2024 will focus on the latest advancements of generative AI in the computer vision domain, with an emphasis on efficiencies across multiple aspects. We encourage techniques that enable generative models to be trained more efficiently and/or run on resource-constrained devices, such as mobile phones and edge devices. Through these efforts, we envision a future where these permeating generative AI capabilities become significantly more accessible with virtuous scalability and plateauing carbon footprint.

The topics involved in the workshop include but are not limited to:

Format: Submissions must use the CVPR 2024 Author Kit for Latex/Word Zip file and follow the CVPR 2024 author instructions and submission policies. Submissions need to be anonymized. The workshop considers two submission tracks:

Only long papers will be included in the CVPR 2024 proceedings.

Submission Site: https://cmt3.research.microsoft.com/CVPREDGE2024

Submission Deadline: March 22, 2024 (AOE) March 27, 2024 (AOE)

Workshop Date: June 17, 2024 (Full Day)

Workshop Location: Summit 432

Virtual Audience: https://cvpr.thecvf.com/virtual/2024/workshop/23675




Speakers


Thomas Leimkühler

Max-Planck-Institut für Informatik

Shanghang Zhang

Peking University

Song Han

Massachusetts Institute of Technology

Björn Ommer

Ludwig Maximilian University of Munich

Jian Ren

Snap Inc.

Cheng Lu

Tsinghua University

Qiang Liu

University of Texas at Austin

Ziwei Liu

Nanyang Technological University




Schedule

Each talk is assigned a 40 min slot (2 min intro + 30 min talk + 5 min QA + 3 min buffer)

Time Activity Title
08:30 - 08:40 Opening remarks
08:40 - 09:20 Georgios Kapanas, Inria / Thomas Leimkühler, MPI "3D Gaussian Splatting: An Introduction and Recent Advancements"
09:20 - 10:00 Shanghang Zhang, Peking University "Towards Machine Learning Generalization in the Open World"
10:00 - 10:10 Morning Break
10:10 - 10:50 Song Han, MIT "Efficient Multi-modal LLM on the Edge"
10:50 - 11:30 Björn Ommer, LMU "Beyond Diffusion: Efficient Models for Visual Synthesis"
11:30 - 12:10 Jiaming Song, Luma AI "Dream Machine"
12:10 - 13:40 Poster Session (Level 4, 4E), Lunch Break
13:50 - 14:30 Jian Ren, Snap Inc. "Content Generation on Mobile Devices"
14:30 - 15:10 Tim Salimans, Google "Two New Distillation Methods for Few-step Generation with Diffusion Models"
15:10 - 15:50 Cheng Lu, Tsinghua University "DPM-Solver: Training-Free Fast Samplers for Diffusion Models"
15:50 - 16:00 Afternoon Break
16:00 - 16:40 Qing Liu, UT Austin "Rectified Flow and Straight Coupling: What is the Mathematical Essense of Fast Generation?"
16:40 - 17:20 Ziwei Liu, NTU "Vchitect: Efficient and Scalable Video Generation"
17:20 - 17:30 Closing remarks  



Accepted Papers


We are pleased to announce the accepted papers for the First Workshop on Efficient and On-Device Generation (EDGE) at CVPR 2024. Congratulations to all authors!

Long Papers

Short Papers




Organizing Committee


Felix Juefei-Xu*

GenAI, Meta

Tingbo Hou*

GenAI, Meta

Licheng Yu

GenAI, Meta

Ruiqi Gao

Google DeepMind

Xiaoliang Dai

GenAI, Meta

Bichen Wu

GenAI, Meta

Chenlin Meng

Stanford University

Ning Zhang

GenAI, Meta

Yanwu Xu

Boston University

Xi Yin

GenAI, Meta

Yunzhi Zhang

Stanford University

Andrew Brown

GenAI, Meta

Ali Thabet

GenAI, Meta

Peizhao Zhang

GenAI, Meta

Peter Vajda

GenAI, Meta




Important Dates






Please contact us (see bottom of this page) if you are interested in sponsoring this workshop!