CARVIEW

MOTORHOMES

Select Language

HTTP/2 200 server: GitHub.com content-type: text/html; charset=utf-8 last-modified: Fri, 31 Oct 2025 08:17:43 GMT access-control-allow-origin: * strict-transport-security: max-age=31556952 etag: W/"690470a7-75c0" expires: Sun, 28 Dec 2025 13:34:34 GMT cache-control: max-age=600 content-encoding: gzip x-proxy-cache: MISS x-github-request-id: 90B8:328FD3:7ABE1A:898C21:69512F90 accept-ranges: bytes age: 0 date: Sun, 28 Dec 2025 13:24:34 GMT via: 1.1 varnish x-served-by: cache-bom-vanm7210072-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1766928274.395074,VS0,VE206 vary: Accept-Encoding x-fastly-request-id: 3ad56142ec49f109973cebe43110dcb2f98508da content-length: 8057 HiGen | ICCV 2025 Workshop

1st Workshop on

Human-Interactive Generation and Editing

ICCV 2025 Workshop (HiGen), Oct 19

About

The rapid evolution of generative AI has reshaped content creation across images, video, and 3D/4D visuals. This workshop focuses on cutting-edge methodologies, practical applications, and open challenges in image/video/3D/4D generation and related editing tasks with an emphasis on flexible and friendly human interactions and multi-modal control signals. This workshop will serve as a platform for researchers and practitioners to discuss key topics related to visual content creation and editing with versatile interactions.

Recap & Highlights

On-site Attendees

Accepted Papers

Best Papers & Orals

Posters

Swipe / scroll → to see more photos

Schedule

Time	Event	Speaker
09:00-09:10	Introduction and Opening Remarks	Organizers
09:10-09:40	Invited Talk 1: Efficient Image and Video Generation with Diffusion Models and Acceleration	Enze Xie
09:40-10:10	Invited Talk 2: The Full Stack Creator: A Unified Stack for Editable and Dynamic 3D Worlds	Yanpei Cao
10:10-10:25	Coffee Break	-
10:25-10:55	Invited Talk 3: Multimodal and Interactive Visual Generation towards World Models	Xihui Liu
10:55-11:25	Invited Talk 4: Towards Unified Generative Models for Image and Video Editing	Soo Ye Kim
11:25-11:55	Invited Talk 5: LongLive: Real-time Interactive Long Video Generation	Yukang Chen
11:25-12:15	Poster Session	-
12:15-13:00	Lunch Break	-
13:00-13:35	Best Paper Talk	TBD
13:30-14:00	Invited Talk 6: From controlling, prompting to real-time interactive video generation	Jimei Yang
14:00-14:30	Invited Talk 7: Customizing Text-to-Image Diffusion Models	Nupur Kumari
14:30-14:40	Coffee Break	-
14:40-15:15	Oral Paper Presentations	-
15:15-15:45	Invited Talk 8: Diffusion Transformers with Representation Autoencoders	Saining Xie
15:45-16:15	Invited Talk 9: Generative Reconstruction and Distillation of Human-Object Interactions	Jiajun Wu
16:15-16:45	Invited Talk 10: BAGEL: The Open-Source Unified Multimodal Mode	Haoqi Fan
16:45-17:15	Invited Talk 11: Audio-visual generation fueled by video learning	Kristen Grauman
17:15-17:30	Closed Remarks	Organizers

Speakers

Enze Xie
NVIDIA

Yukang Chen
NVIDIA

Jimei Yang
Runway

Soo Ye Kim
Adobe

Yanpei Cao
VAST

Saining Xie
NYU

Jun-Yan Zhu
CMU

Nupur Kumari
CMU

Haoqi Fan
Bytedance Seed

Kristen Grauman
UT Austin

Jiajun Wu
Stanford University

Xihui Liu
HKU

Call for Papers

Topics

Topics of interests include, but are not limited to:

Interactive content creation and editing
Controllable generation with multi-modal interaction
Cross-domain cooperation for visual generative models
Generative world exploration and human object interaction
Foundational designs (pipeline, model, operator, etc.) for AIGC

Submission Guidelines

All papers must be submitted via the ICCV 2025 OpenReview workshop website.
Submission should be PDF format and follow the official ICCV 2025 template and guidelines.
Authors may upload optional supplementary materials, containing additional details, videos, images, etc.
Papers should follow the ICCV author guidelines and be anonymized for double-blind review.
The accepted papers will be presented as oral, or poster presentations.
The presentation of accepted papers at our workshop will follow the same policy as that for the accepted papers at the ICCV 2025 leading conference.
One Best Paper Award ($800) and one Runner-up Award ($400) will be granted to the most outstanding contributions, selected based on originality, technical merit, and potential impact from the accepted papers.

Submission Track 1: Proceedings Track

Submissions are expected to present original, unpublished work, and should be longer than 4 pages in length (up to 8 pages, including figures and tables but excluding references). Accepted papers will be published in the official ICCV workshop proceedings.

Important Dates (All deadlines are 23:59 UTC)

Paper Submission Deadline: ~~June 30~~ July 5, 2025
Author Notification of Acceptance: ~~July 10~~ July 12, 2025
Camera-ready Submission: August 9, 2025
Workshop Date: October 19, 2025

Submission Portal: Proceedings

Submission Track 2: Non-Proceedings Track

The Non-Proceedings Track offers a more flexible avenue for presenting a wider range of contributions without page limits. Accepted papers will NOT be published in the official ICCV workshop proceedings, but they can be presented and promoted as oral or poster presentations at our workshop. Submissions include but are not limited to:

Extended abstracts and short papers: We welcome submissions of up to 4 pages that describe work still in progress that is valuable to the community, or articulate insightful position papers on relevant topics.
Previously published work: We also accept submissions of work that has already been published elsewhere. This includes papers that may have been accepted at the main ICCV 2025 conference itself.

Important Dates (All deadlines are 23:59 UTC)