2nd Workshop on Efficient and On-Device Generation (EDGE)

AdaVid: Adaptive Video-Language Pretraining

Chaitanya Patel,

Juan Carlos Niebles,

Ehsan Adeli

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Patel_2025_CVPR, author = {Patel, Chaitanya and Niebles, Juan Carlos and Adeli, Ehsan}, title = {AdaVid: Adaptive Video-Language Pretraining}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {6389-6398} }

Latent Patched Efficient Diffusion Model For High Resolution Image Synthesis

Weiyun Jiang,

Devendra Kumar Jangid,

Seok-Jun Lee,

Hamid Rahim Sheikh

[pdf]

[bibtex]

@InProceedings{Jiang_2025_CVPR, author = {Jiang, Weiyun and Jangid, Devendra Kumar and Lee, Seok-Jun and Sheikh, Hamid Rahim}, title = {Latent Patched Efficient Diffusion Model For High Resolution Image Synthesis}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {6372-6378} }

ADAPTOR: Adaptive Token Reduction for Video Diffusion Transformers

Elia Peruzzo,

Adil Karjauv,

Nicu Sebe,

Amir Ghodrati,

Amir Habibian

[pdf]

[bibtex]

@InProceedings{Peruzzo_2025_CVPR, author = {Peruzzo, Elia and Karjauv, Adil and Sebe, Nicu and Ghodrati, Amir and Habibian, Amir}, title = {ADAPTOR: Adaptive Token Reduction for Video Diffusion Transformers}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {6365-6371} }

Scaling On-Device GPU Inference for Large Generative Models

Jiuqiang Tang,

Raman Sorokin,

Ekaterina Ignasheva,

Grant Jensen,

Lin Chen,

Juhyun Lee,

Andrei Kulik,

Matthias Grundman

[pdf]

[bibtex]

@InProceedings{Tang_2025_CVPR, author = {Tang, Jiuqiang and Sorokin, Raman and Ignasheva, Ekaterina and Jensen, Grant and Chen, Lin and Lee, Juhyun and Kulik, Andrei and Grundman, Matthias}, title = {Scaling On-Device GPU Inference for Large Generative Models}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {6355-6364} }

LLMPi: Optimizing LLMs for High-Throughput on Raspberry Pi

Mahsa Ardakani,

Jinendra Malekar,

Ramtin Zand

[pdf] [arXiv]

[bibtex]

@InProceedings{Ardakani_2025_CVPR, author = {Ardakani, Mahsa and Malekar, Jinendra and Zand, Ramtin}, title = {LLMPi: Optimizing LLMs for High-Throughput on Raspberry Pi}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {6379-6388} }

Geometric Consistency Refinement for Single Image Novel View Synthesis via Test-Time Adaptation of Diffusion Models

Josef Bengtson,

David Nilsson,

Fredrik Kahl

[pdf] [arXiv]

[bibtex]

@InProceedings{Bengtson_2025_CVPR, author = {Bengtson, Josef and Nilsson, David and Kahl, Fredrik}, title = {Geometric Consistency Refinement for Single Image Novel View Synthesis via Test-Time Adaptation of Diffusion Models}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {6399-6408} }