@jbhuang0604 The really sad part is that many speakers are actually presenting someone else’s work because the authors could not travel to present in person
We have an amazing lineup of invited speakers
Maaike Van Roy, KU Leuven
Atom Scott, Founder of Playbox Inc.
Christina Chase, Co-founder and Managing Director at MIT Sports Lab
Johsan Billingham, Senior research manager at FIFA
https://t.co/pVqjnQJSYa
Are you at #cvpr 2026 and already feeling the fever for the World Cup? Or just interested in how Computer Vision is used in sports? Come June 4th to Room 503 for the Computer Vision in Sports Workshop!
https://t.co/EwOJUfcxcz
#cvpr#cvsports
Very proud of this Publication in npj Digital Medicine!
An interpretable, attention-based AI model to assess dysarthria severity from remotely collected speech recordings.
🔗 Open-access article:
https://t.co/ZzPiRai2YE
with Kely Norel, Carla Agusto Rios and Guillermo Cecchi
Congratulations to all authors who submitted their papers to our CVsports workshop today! 🚀 Once again, we’ve received a record number of submissions this year. Next steps: reviews and author notifications on March 27, 2025. Good luck, and hopefully see you at @CVPR! 🙌
🎉Today, we're pleased to announce the release of the Granite 3.0 model family, the latest open-licensed, general purpose LLMs from @IBM 🎉
These have been a labor of love for my team at @IBMResearch, working closely with a host of collaborators across the company. We're excited to share them with you.
Some key details:
📏 available in 4 sizes, ranging from 400m to 8B active parameters, with both dense transformer (2B and 8B) and mixture-of-experts (3B-A800M and 1B-A400M) versions.
💪 strong performance across a range of tasks (see figure below), standing toe-to-toe with the best open models in their weight class.
⚡️fast and light, designed to run anywhere, from GPU servers to CPUs and edge devices. We have also released a companion speculator model—Granite Accelerator—which can more than double the speed of the 8B model.
🏦 built with business in mind, with a permissive Apache 2.0 open source license, and special focus on enterprise tasks. Multlingual, coding task-enabled, and with built-in function-calling support for agentic patterns
🔎 comprehensive transparency—our technical report carefully details the data sources that went into our models, along with details on how we trained them.
🏰 Companion Granite Guardian models are available in 2B and 8B sizes that achieve state-of-the-art input and output guardrail performance
🌱 Built using 100% renewable energy
We received the Best Paper Award at the 2024 IEEE International Conference on Digital Health! Amazing to work with Carla Agurto, Kely Norel and team on analyzing speech for early detection of ALS biormarkers.
https://t.co/Gdg9dYtQow
@RGiryes@MattNiessner We have it already! Just did the 10 year anniversary https://t.co/EwOJUfbZn1
We also cover the application of semi-automatic offside in this book chapter, although unfortunately fine grained details on the exact setup are lacking from the source
https://t.co/Bw4UQ9H5VG
polish TV is using computer vision to enhance the viewer experience for sports broadcasts:
- FIFA-like radar overlays
- player recognition
- pass distance measurement
- ball speed and trajectory tracking during shots
The (Computer) Vision of Sports book chapter is finally out!
had a lot of fun working on this with
Professors Rikke Gade, Graham Thomas and Thomas Moeslund
https://t.co/oVfj4PE5N6
Interested in LLM-based Code Translation 🧐?
Check our CodeLingua leaderboard (https://t.co/GS3MADfW6D). We have updated the leaderboard with newly released Granite code LLMs from @IBMResearch. Granite models outperform Claude-3 and GPT-4 in C -> C++ translation 🔥.
Amazing release from @IBM: Fully transparent Granite Code models! 🚀
Comes in 3B, 8B, 20B and 34B sizes with base and instructions models and are pretrained on The Stack and high quality sources🔥
Models: https://t.co/0VFXS28rhn
Paper: https://t.co/VzT5cHnV13
Congrats team!
Only a bit more than 4 days left to submit your paper to our CVsports workshop @CVPR! ⏰
Time to refine... or start writing? 😏
🌐https://t.co/wKyTgxCkml
#Deadline#CVPR2024#Sports#AI#Workshop