We update you on the NU Sports ML Workshop scheduled for Aug 19-20, 2026!
📅 Registration is now open! (both on-site and online)
➡️ Register here: https://t.co/pArJwuOx0u
🗓️ Registration Deadline: July 15th, 2025
✅ Workshop Schedule (Tentative): https://t.co/3WwaQeqbXD
Workshop Overview:
✅ Day 1 (Hybrid): Invited Talks and Oral Presentations
🎤 Keynote Talk: Sang-Ki Ko (University of Seoul)
🎤 Invited Talk 1: Hyunsung Kim (KAIST & Fitogether)
🎤 Invited Talk 2 : Pegah Rahimian (Uppsala University)
✅ Day 2 (In-Person Only): Tutorial on OpenSTARLab RLearn and Open Lab Hours
Currently, there is no registration fee planned, but registration is mandatory. Participation will not be possible without registration by the deadline.
We look forward to your participation!
Organizers: Ding Ning, Calvin Yeung, Kazuhiro Yamada, @Kenjiro_610
@_ConferenceList Two tracks in #MUWS2026
Track 1 — Human-Centred Multimodal Understanding.
Track 2 — Multimodal Understanding Through Impactful World Events. This year's dataset will cover news and social media content from major global events to promote multilingual, multicultural AI research.
@_ConferenceList This is the 5th edition of MUWS, co-located with ACM Multimedia 2026 in Rio 🇧🇷, bringing together researchers from computer science, digital humanities, semiotics, social sciences, and psychology to tackle multimodal understanding from a deeply human-centred perspective.
Our paper was accepted to PAKDD 2026 special session on Data Science: Foundations and Applications (DSFA).
Tang et al., Facet-Level Persona Control by Trait-Activated Routing with Contrastive SAE for Role-Playing LLMs
My first paper on psychology-related conference was accepted!
Ayano Yasui, Takahiro Komamizu, Tomohiro Masuda, “Evaluation of LLM to Likert-type Psychometric Scale Assessment”, ICAP, 2026
Our paper was accepted to #MMAsia2025 !
J. Chen, et al., “Q-Adapter: Visual Query Adapter for Extracting Textually-related Features in Video Captioning”, MMAsia 2025
Our paper was accepted to #FG2026!
Trung Thanh NGUYEN, Yasutomo Kawanishi, Vijay John, Takahiro Komamizu, Ichiro Ide , “View-aware Cross-modal Distillation for Multi-view Action Recognition”, FG 2026
🚀 Excited to introduce Qwen-Image-Edit!
Built on 20B Qwen-Image, it brings precise bilingual text editing (Chinese & English) while preserving style, and supports both semantic and appearance-level editing.
✨ Key Features
✅ Accurate text editing with bilingual support
✅ High-level semantic editing (e.g. object rotation, IP creation)
✅ Low-level appearance editing (e.g. addition/delete/insert)
Try it now: https://t.co/r2Zcg4OjGc
Hugging Face: https://t.co/jfCS6b0W5O
ModelScope: https://t.co/NwbfHlXonE
Blog: https://t.co/VGDdwKuwHy
Github: https://t.co/A9yvJZ6TJc
API: https://t.co/uaumRmgcGG
Two of our papers have been accepted for ACPR 2025.
H. Kato et al., “Origami Crease Recognition for Automatic Folding Diagrams Generation”, ACPR 2025
K. Ikeda, et al., “Lip Shape-aware Word Selection for Lyric Translation”, ACPR 2025