Introducing Griffin, the first model to pass the video Turing test.
48% of people who talked to it live thought it was a real human. Previous systems have had a pass rate <3%. It is #1 on NVIDIA's benchmark for full-duplex AI video.
It’s the first Human Interaction Model (HIM).
Readers added context they thought people might want to know
The 48% figure and "video Turing test" claim are from Tavus's own study of 54 one-minute calls, not independently verified or using a standard protocol. Griffin-Lite leads NVIDIA's VideoFDB benchmark on their public leaderboard.
cellcog.ai/blog/tavus-gri…
research.nvidia.com/labs/amri/proj…
tech-ish.com/2026/10/02/tav…
Seonwook Park (Wookie) retweeted
Excited to release VideoFDB: the first benchmark for full-duplex audio-visual-to-audio-visual (AV2AV) conversational agents. VideoFDB tests whether models can act as active interlocutors in 1:1 conversation, not just answer questions about video.
Seonwook Park (Wookie) retweeted
🎉 Announcing the first Interactive Physical AI Workshop at #CVPR2026.
Join us for a half-day workshop exploring AI systems that see, communicate, and act safely in our shared physical world — including robots, environment-aware avatars (e.g., AR telepresence), and on-device multimodal agents.
✅ Cross-disciplinary topics spanning vision, robotics, and multimodal AI
✅ Featuring invited speakers (incl. Yaser Sheikh @subail), poster sessions, and spotlight talks
📅 Paper deadline is Feb 28: openreview.net/group?id=thec…
More info: research.nvidia.com/labs/amr…
🙌 Organized by: @swookpark, @amritamaz, @mct1224, @lmathur_, @luminohope and @shalinidemello
💡 Sponsored by NVIDIA.
We look forward to seeing you at CVPR.
Proud to be organizing the 1st IPA workshop with my colleagues. We are accepting full-paper submissions and have exciting keynote speakers lined up!
Please take a look if you're interested in how to improve interactive experiences between humans and Physical AI systems.
📢IPA 2026 (Interactive Physical AI) @CVPR 2026.
Announcing the 1st Interactive Physical AI workshop at CVPR 2026! This half-day workshop will bring together researchers to discuss AI systems that perceive humans and scenes, communicate via multimodal signals, and act safely in our shared physical world. 🧵
#CVPR2026
4
82
Seonwook Park (Wookie) retweeted
excited to announce ▶️Play4D: efficient dynamic 4D neural scene reconstruction, for physical AI, VR, and light field displays!
see it live at #SIGGRAPHAsia2025 Emerging Technologies in Hong Kong!
🔗 research.nvidia.com/labs/amr…
Seonwook Park (Wookie) retweeted
Learned from in-the-wild images, GAIA generates 3D Gaussian animatable avatars with identity & expression control and real-time animation
📅 Talk: Aug 14, 9 AM PDT – West Bldg, Rm 211–214
🎮 Live demo @ poster session & E-Tech
🔗research.nvidia.com/labs/amr…
#SIGGRAPH2025 @NVIDIAAI
Seonwook Park (Wookie) retweeted
Don't miss the "Volumetric Video in the Real World" tutorial at #CVPR2025 on 6/11
Hear from top academic & industry experts on innovations, opportunities and challenges in 4D reconstruction and generation of immersive scenes, digital humans and autonomous driving.
🔗: nvda.ws/45E8x45
Seonwook Park (Wookie) retweeted
Join us for "Volumetric Video in the Real World", a tutorial on 4D research @CVPR in Nashville, on Wednesday June 11 from 9am-5pm in Room 205B #CVPR2025 !
With amazing experts @holynski_ @c_richardt @iamborisi @yiyi_liao_ @sharathgirish97 & Lan Xu
🔗nvlabs.github.io/cvpr2025-vo…
I'm very proud to be recognized as an "Outstanding Reviewer" for CVPR 2023 - they were very selective this time, picking just 3.3%!
We sincerely thank all reviewers, area chairs and senior area chairs who contributed their time to #CVPR2023! Reviewers who did an outstanding job are recognized here: cvpr2023.thecvf.com/Conferen…
15
1,523
Seonwook Park (Wookie) retweeted
And, the Oscar award goes to CMT that went down just before the #CVPR2022 deadline.
Seonwook Park (Wookie) retweeted
I'm very pleased to announce that our new book on "Artificial Intelligence for Human Computer Interaction: A Modern Approach" is now available.
link.springer.com/book/10.10… I'd like to thank my co-editor Otmar Hilliges, 50+ chapter authors, and Peter Norvig for writing the forward.
Seonwook Park (Wookie) retweeted
Our team at Facebook Reality Lab Research is hiring Research Scientist interns for the coming year. Feel free to contact me or @Stephanie_FRL if you have interests! Will be great if you can share the message to anyone who may have interests!
facebook.com/careers/v2/jobs…
Seonwook Park (Wookie) retweeted
A. Krause, T. Hofmann, O. Hilliges and K. P. Prüssmann are four leading @ETH Zurich scientists who have been appointed Max Planck Fellows at MPI-IS, further boosting our successful #research partnership, the #MaxPlanck ETH Center for Learning Systems: is.mpg.de/news/leading-eth-z…
Seonwook Park (Wookie) retweeted
Hi, I am still looking for a PhD student at TU Delft on gaze estimation. You are welcome to forward the link: tudelft.nl/over-tu-delft/wer…
Seonwook Park (Wookie) retweeted
We are thrilled to announce a groundbreaking partnership with @GuardantHealth! The deal includes strategic investment of $26 million from Guardant to #Lunit, intended to reshape and innovate the precision oncology landscape. #cancer #AI
prnewswire.com/news-releases…
Seonwook Park (Wookie) retweeted
#CVPR2021 Workshop GAZE2021: Gaze Estimation and Prediction in the Wild is going on right now! We have fantastic invited speakers, paper presentations (oral+poster), challenge winner talks, and live panel discussion.
Come join our workshop: gazeworkshop.github.io/2021/
GAZE 2021 is now ongoing. Please tune in via the official channels (Zoom) or via links located at gazeworkshop.github.io/2021/ to catch up on the latest in gaze estimation and prediction in the wild!
Seonwook Park (Wookie) retweeted
We are hosting a workshop on GAZE2021: Gaze Estimation and Prediction in the Wild on June 20 (Sunday) at 11 am EDT. We have fantastic invited speakers, paper presentations (oral+poster), challenge winner talks, and live panel discussion.
For more details:
gazeworkshop.github.io/2021/




















