The boundary between reality and the virtual world is about to disappear.
Imagine characters from Pokemon or Digimon coming to life—not on a screen, but right in front of you. You reach out, and they respond.
Introducing X1.
The first real-time interactive video model that brings imagination into reality.
Built by the Xmax AI team from Tsinghua University.
Let’s Play the World through AI.
Repost & comment to join the X1 private beta (free).
How did we get here? In real-time discussions, ideas get lost and conversations drift. EchoMind is a human-AI facilitation tool that organizes discussions into live issue maps, keeping teams focused and productive. ✅story, video & code #CSCW2025@ACM_CSCW https://t.co/8Owi2GjkHg
This work marks a milestone in developing a more comprehensive and nuanced understanding of human actions. Our two IMWUT papers have demonstrated that Human Activity Recognition (HAR) provides crucial context for richer semantic action understanding, both in ages of DL and LLMs.
Congrats to #Tsinghua University's Pervasive HCI Lab @thuhci & West China Hospital's @IHuaXi Rehab Medicine Center for winning the #IMWUT Distinguished Paper Award at #UbiComp2025 for "UbiPhysio"! 🏆Their innovative study combines biomech with LLMs to deliver home rehab guidance.
First time @ubicomp, presenting and demoing RingMind: our lab-built smart ring (mic+IMU) + LLMs to understand speech & gesture in natural settings. A step toward human-AI cognitive alignment through multimodal interfaces.
Next: CSCW sharing EchoMind and excited to connect!
Prof. Chen Ning Yang, a world-renowned physicist, Nobel Laureate in Physics, Academician of the Chinese Academy of Sciences, Professor at Tsinghua University, and Honorary Director of the Institute for Advanced Study at Tsinghua University, passed away in Beijing due to illness at the age of 103. His life stands as a timeless chapter in human history—one that shines not only for China but for the global community of thinkers and innovators. His legacy will live on forever.
"The first AGI will be Federated" -- come hear my keynote at the @AcmSensys conference this Wednesday morning. I'll explain why when we finally achieve AGI, and flick the switch to bring it online, it will have been trained using some variety of federated AI. And not the training methods of today, DDP and the like, that are limited to being deployed in single data centers -- which are themselves fast reaching the limits of their own scalability as we struggle to co-locate and power north of 100k GPUs in one physical place.
In support of my talk, here is a preview of a few results coming in hot from a new arxiv paper produced by @flwrlabs and @CaMLSys (@Cambridge_Uni) that will go live also Wednesday. We show our unique approach and system (aka Photon built on Flower) produces LLMs that are both better (by perplexity) and faster to train than DDP (when network speeds are equal, as measured up to 7B). Furthermore, we show this can scale effectively as we add more weakly connected GPUs -- while also being more efficient (eg better wall clock training times) than any existing known methods for training under decentralized/widely-distributed settings.
Folks, it's time to train different. Larger and more complex LLM settings are underway. Link to arxiv Wednesday.
🤟I’m so happy to see such a big response to the launch of the FlowerTune LLM Leaderboard!
➡️Complete launch details: https://t.co/6Gn0AkR1hf
🦙Visit the leaderboard and participate now: https://t.co/cRR9XsboJo
Our iconic summer program #ACSP is opening for applications, a good platform for students to get involved with cutting-edge HCI projects and gain opportunities for graduate studies!📚🔬
Paper: https://t.co/vhnRfCYeNg
Code (currently blank given our small team busy opening other projects, please star🌟 to motivate us😄): https://t.co/f0vRJa1PN3
Presented my first #CHI2024 paper today! I was thrilled to receive warm reactions from the audiences. For sure, PepperPose shall open a new route for future interactions driven by human actions. The goal is to waive users from wearing devices and allows them to move/act freely.🙂
We prepared a special trifold booklet with our presentation papers & session info, and iconic works. 📚
Didn't get one? No worries! Check out below the online version or find a @thuhci member on-site! 💻🔍 #CHI2024
First day at #CHI2024 in Hawaii! 🌴🌺
@thuhci team is excited to be here~🎉
Today, we had a great time meeting with some amazing HCI pioneers (Jussi P. P. Jokinen from University of Jyväskylä during, and Neha Kumar @nehakumar )! 📸✨
Flower is connecting with it's global community today: 🇰🇷🇪🇸🇩🇪🇨🇳🇬🇧🇫🇷🇺🇸🇮🇳... and many more! And most importantly, we are doing it with a zero carbon 👣foot print. 😎
🌼 Flower around the 🌐World is powering ahead. 🇰🇷Korean finished about an hour ago (thank you @YoungDKwon1!). Now in the middle of the 🇨🇳chinese session (courtesy of Pan Heng!) Here is a behind-the-scenes-look from the zoom war room; join the fun now at: https://t.co/bsnEdqH4AG
🌼 Flower around the 🌐World is powering ahead. 🇰🇷Korean finished about an hour ago (thank you @YoungDKwon1!). Now in the middle of the 🇨🇳chinese session (courtesy of Pan Heng!) Here is a behind-the-scenes-look from the zoom war room; join the fun now at: https://t.co/bsnEdqH4AG
[DDL: 12 May]
Waiting for your submissions to our 2nd workshop on Affective Human-Robot Interaction (AHRI 2023 https://t.co/aMl2tPBK5H) at #ACII2023@acii_conf@officialAAAC