Overview

Note: ASL interpreters will be available throughout the workshop.

    Welcome to GenSign: The 1st Workshop on Generative AI for Sign Language at CVPR 2026!

    Recent advances in sequential generative models and diffusion-based approaches offer a promising pathway to produce high-quality translations, synthesize realistic and expressive digital signers, expand low-resource sign datasets, and foster more inclusive communication between deaf and hearing communities.

    This workshop brings together researchers from computer vision, natural language processing, linguistics, and accessibility studies to explore the frontiers of generative modeling for sign language and to foster responsible, human-centered AI systems that understand and communicate through this uniquely visual language. Specifically, we aim to:

    • Advance generative approaches for sign language understanding and generation, including high-quality translations, realistic and expressive digital signer synthesis, and expansion of low-resource sign datasets.
    • Leverage modern sequential and diffusion-based models to address realism, controllability, and data scarcity in low-resource sign language settings.
    • Promote responsible and inclusive AI systems that respect linguistic structure and meaningfully support deaf and hard-of-hearing communities.

Call for Papers

We welcome contributions covering all aspects of generative AI for sign language:

🤟 Generative Foundation Models

Pre-trained visual-linguistic and generative models to capture sign structure and boost downstream tasks.

🎨 Sign-Aware Expressive Generation

Sign-aware generation for natural, expressive signing with higher linguistic fidelity.

🔗 Multi-modal Inclusive Communication

Cross-modal representations and real-time translation across vision, text, and speech.

🌉 Syn-to-Real Sign Data Infrastructure

Synthetic data, domain adaptation, and evaluation for robust cross-domain generalization.

⚖️ Ethical & Societal Perspectives

Governance, fairness, consent, and community-aligned social impact.

Submission Track 1: Proceedings Track

Submissions must present original, unpublished research and follow the CVPR 2026 template.

  • Length: 5-8 pages (main text), excluding references and optional appendices
  • Review Process: Double-blind peer review via OpenReview, all manuscripts must be fully anonymized
  • Publication: Accepted papers will be published in workshop proceedings
  • Code & Data: Open-sourcing is encouraged but not mandatory
  • Presentation: All accepted papers are expected to be presented in person at the workshop

Important Dates (AoE)

  • Paper Submission Deadline: March 14, 2026
  • Author Notification: March 20, 2026
  • Camera Ready: April 10, 2026

Submission Track 2: Non-Proceedings Track

A flexible, non-archival track for sharing work without restrictive formatting or page limits.

  • Works-in-progress and preliminary results
  • Open datasets, technical reports, and recent submissions
  • Position papers and conceptual frameworks
  • Previously published work accepted

Important Dates (AoE)

  • Paper Submission Deadline: April 14, 2026
  • Author Notification: April 4, 2026
  • Camera Ready: May 11, 2026

Invited Speakers

We are honored to host distinguished academic and industry experts on generative AI for sign language.

Richard Bowden

Richard Bowden

University of Surrey & Signapse AI

Richard Bowden is Professor of Computer Vision and Machine Learning at the University of Surrey, UK, where he leads the Cognitive Vision Group within the Centre for Vision Speech and Signal Processing. He is also Co-founder and Chief Scientist of Signapse AI. His research focuses on computer vision for human detection, tracking, and understanding. He is a Fellow of the Higher Education Academy, a senior member of the IEEE, a Fellow of the International Association of Pattern Recognition, and Distinguished Fellow of the BMVA.

Karen Livescu

Karen Livescu

Toyota Technological Institute at Chicago

Karen Livescu is Professor at TTIC and a part-time Associate Professor at the University of Chicago. Her research interests span speech and language processing, multimodal learning, and representation learning, with a focus on self-supervised models, speech-text integration, and sign language understanding. She is a Fellow of IEEE and ISCA, and served as a Distinguished Lecturer of the IEEE Signal Processing Society. Her research has been recognized with the Best Paper Award at EMNLP 2024 and ICML Test of Time Runner-Up.

Chris Dyer

Chris Dyer

Google DeepMind

Chris Dyer is Principal Scientist at Google DeepMind, where he leads the SignGemma project. His research lies at the intersection of natural language processing, computational linguistics, and machine learning, with significant contributions to statistical and neural machine translation, probabilistic modeling, and large-scale text processing. He co-developed widely used NLP frameworks such as cdec. He has served on program committees for major NLP conferences, including ACL, EMNLP, and NAACL.

Abraham Glasser

Abraham Glasser

Gallaudet University

Abraham Glasser is Assistant Professor at Gallaudet University. His research focuses on accessible computing, human–computer interaction, and immersive technologies for Deaf and Hard-of-Hearing users. He has served as the Accessibility Chair of ACM ASSETS, Associate Chair of ACM CHI, etc. He is also a member of the Coalition for Sign Language Equity in Technology (CoSET). He has presented award-winning research at major international venues, including Best Poster at ACM VRST and Impact Paper Award at ACM CSCW.

Workshop Schedule

The workshop will be held as an afternoon session at CVPR 2026 in Nashville, Tennessee.

Note: ASL interpreters will be available throughout the workshop.

TimeSessionSpeaker / Details
13:00 - 13:10WelcomeOpening Remarks by Organizers
13:10 - 13:40Keynote 1TBD
13:40 - 14:10Keynote 2TBD
14:10 - 15:00Coffee BreakPoster Session
15:00 - 15:30Keynote 3TBD
15:30 - 16:00Keynote 4TBD
16:00 - 16:30Keynote 5TBD
16:30 - 17:00Oral PresentationsSelected Paper Presentations
17:00 - 17:30Panel DiscussionFuture Directions & Community Engagement
17:30 - 17:40ClosingClosing Remarks & Next Steps

Organizers

Our organizing team brings together expertise from computer vision, NLP, linguistics, and accessibility research across multiple continents.

Hezhen Hu

Hezhen Hu

University of Texas at Austin

Yuecong Min

Yuecong Min

Institute of Computing Technology, CAS

Ronglai Zuo

Ronglai Zuo

Imperial College London

Oscar Koller

Oscar Koller

Microsoft Research, Munich

Léore Bensabath

Léore Bensabath

École des Ponts ParisTech

Wengang Zhou

Wengang Zhou

University of Science and Technology of China

Houqiang Li

Houqiang Li

University of Science and Technology of China

Stefanos Zafeiriou

Stefanos Zafeiriou

Imperial College London & Google

Xilin Chen

Xilin Chen

Institute of Computing Technology, CAS

Hongdong Li

Hongdong Li

Australian National University

Dimitris N. Metaxas

Dimitris N. Metaxas

Rutgers University