Gen4AVC Workshop | ECCV 2026

Workshop Overview

Seamless integration of audio and visual elements is crucial for creating immersive and engaging content. Audio-visual generation, involving the synthesis of one modality from the other or both jointly, has become a key research area. This capability holds significant potential for applications like virtual reality, gaming, film production, and interactive media, using advanced generative models to enhance multimedia quality and realism.

This workshop highlights the growing importance of audio-visual generation in modern content creation, bringing together researchers and practitioners from academia and industry to explore the latest advances, challenges, and emerging opportunities in this dynamic field.

Topics Include:

Joint Audio-Visual Generation
Vision-to-Audio and Audio-to-Vision Synthesis
Audio-Visual Editing
Interactive Creation
World Modeling and Streaming
Evaluation and Reliability

Schedule

Morning Session, September 8th, 2026

Note: All times are in Central European Summer Time (CEST).

9:00 - 9:05

Opening Remarks

Welcome and introduction to the workshop

9:05 - 9:45

Invited Talk 1: Cusuh Ham

Adobe Research

"Generating B-Roll Sequences from User Video Collections"

9:45 - 10:00

Coffee Break & Poster Setup

Authors set up posters

10:00 - 11:00

Poster Session (MalmöMässan Exhibit Hall)

Poster presentations - see the poster list below

11:00 - 11:40

Invited Talk 2: Ofir Bibi

Lightricks

"Control from Within: Activating the Controls LTX Already Knows"

11:40 - 12:20

Invited Talk 3: Ruohan Gao

University of Maryland

"From Audio-Visual Objects to Audio-Visual Spaces"

Poster Presentations

Regular Posters

Diverse Dance Video Generation from a Single Music Input

Author: Nokap Tony Park
Grounding the Visual Axis of a Narrative World Model: Consistency-Aware Reference Generation for Long-Form Stories

Authors: Divyajot Singh, Imon Banerjee, Shourya Gupta, Aaryaman Jain, Shreyash Mishra, Vasu Sharma
Adding Voice Cloning to Text-to-Audio-Video Models with a Single Zero-Initialised Layer

Authors: Mikheev Ivan, Viacheslav Vasilev, Anna Dmitrienko, Alexey Letunovskiy, Ivan Kirillov, Kirill Chernyshev, Denis Dimitrov
RealMaster: Lifting Rendered Scenes into Photorealistic Video

Authors: Dana Cohen-Bar, Ido Sobol, Raphael Bensadoun, Shelly Sheynin, Oran Gafni, Or Patashnik, Daniel Cohen-Or, Amit Zohar
What Do Audio-Visual Synchronization Metrics Actually Measure?

Authors: Jai Kumar Sharma, Peeyush Tapadiya
AURA: AUdio-dRiven streaming Avatar

Authors: Nathaniel Cohen, Nicolas Dufour, Amelie Royer, Alasdair Newson, Patrick Perez

Invited Posters

Objects as Audio-Visual Modal Sound Fields

Authors: Zisen Shao, Zihao Wei, Derong Jin, Ruohan Gao

ECCV 2026
Step-by-Step Video-to-Audio Synthesis via Negative Audio Guidance

Authors: Akio Hayakawa, Masato Ishii, Takashi Shibuya, Yuki Mitsufuji

ECCV 2026
OmniForcing: Unleashing Real-time Joint Audio-Visual Generation

Authors: Yaofeng Su, Yuming Li, Zeyue Xue, Jie Huang, Siming Fu, Haoran Li, Ying Li, Zezhong Qian, Haoyang Huang, Nan Duan

ECCV 2026
JoVA: Unified Multimodal Learning for Joint Video-Audio Generation and Editing

Authors: Xiaohu Huang, Haoyang He, Hao Zhou, Qiangpeng Yang, Shilei Wen, Kai Han

ECCV 2026

Important Dates

Paper Submission (Regular Track)

~~July 2, 2026 23:59 AoE (Anywhere on Earth)~~

July 9, 2026 23:59 AoE (Anywhere on Earth)

Paper Submission (Invited Track)

~~August 10, 2026 23:59 AoE (Anywhere on Earth)~~

August 17, 2026 23:59 AoE (Anywhere on Earth)

Decision Notification

August 9, 2026

Camera Ready

August 17, 2026 23:59 AoE (Anywhere on Earth)

Workshop Date

September 8 (AM), 2026

Location: Quality View Oresundslokalen - C

Call for Papers (Regular Track)

Overview

We welcome submissions on (but not limited to) the following topics:

Joint Audio-Visual Generation
Vision-to-Audio and Audio-to-Vision Synthesis
Audio-Visual Editing
Interactive Creation
World Modeling and Streaming
Evaluation and Reliability

Submission Guidelines

Papers are limited to four pages in the CVPR style, excluding references and appendices.

Submissions should be made through the OpenReview submission system.

Important Dates

Paper Submission Deadline: July 9, 2026 23:59 AoE (Anywhere on Earth)
Decision Notification: August 9, 2026
Camera Ready Deadline: August 17, 2026 23:59 AoE (Anywhere on Earth)

Review Process

All submissions will undergo a double-blind review process. Please ensure that your submission does not contain any identifying information about the authors.

Publication

The workshop will be non-archival. Authors of accepted papers retain the full copyright of their work and are free to submit extended versions to conferences or journals.

Call for Papers (Invited Track)

We also welcome papers that have been accepted to ECCV 2026 or were presented at recent top-tier conferences (e.g., CVPR, ECCV, NeurIPS, ICML, ICLR, AAAI). Invited papers can be submitted as-is and will not undergo a formal peer review process. Accepted submissions will be presented as invited posters at the venue. Please apply using the invited poster application form.

Application deadline: August 17, 2026 23:59 AoE (Anywhere on Earth).