iiinova — where your digital self keeps evolving

Reposted by Valentina Giunchiglia

logconference.bsky.social @logconference.bsky.social · 17/06/2026

📢 Call for Papers – LoG 2026 Paper submissions are now open for LoG 2026! Submit your work on any areas broadly related to learning on graphs and geometry 🔗 logconference.org/cfp/ 📅 Key dates (AoE): • July 29 – Abstract deadline • Aug 1 – Full paper deadline #LoG2026

logconference.org

Learning on Graphs Conference

044

Reposted by Valentina Giunchiglia

logconference.bsky.social @logconference.bsky.social · 17/06/2026

📢 Call for Tutorials – LoG 2026 Tutorial proposals are now open for LoG 2026 Submit your proposal and help shape this year’s tutorial program! 🔗 logconference.org/call-for-tut... 📅 Key dates (AoE): • Sept 4 – Proposal deadline • Sept 14 – Notification #LoG2026 #LearningOnGraphs

logconference.org

Learning on Graphs Conference

032

Reposted by Valentina Giunchiglia

logconference.bsky.social @logconference.bsky.social · 17/06/2026

📢 Call for Reviewers – LoG 2026 Help shape the next edition of LoG by reviewing submissions at the intersection of graphs, machine learning, and real-world applications. Top reviewers will receive monetary rewards. 🔗 logconference.org/call-for-rev... #LoG2026

logconference.org

Learning on Graphs Conference

032

Reposted by Valentina Giunchiglia

PantheonOS @pantheonos.bsky.social · 21/08/2025

🚀 Introducing PantheonOS A Fully Open-Source Agent OS for Science PantheonOS began as a research project in Qiu Lab @ Stanford and has since evolved into a vision to redefine data science in the era of AI—starting with computational biology, especially single-cell and spatial genomics.

111

Reposted by Valentina Giunchiglia

LOGML Summer School @logml.bsky.social · 11/03/2025

🌟Applications open- LOGML 2025🌟 👥Mentor-led projects, expert talks, tutorials, socials, and a networking night ✍️Application form: logml.ai 🔬Projects: www.logml.ai/projects.html 📅Apply by 6th April 2025 ✉️Questions? logml.committee@gmail.com #MachineLearning #SummerSchool #LOGML #Geometry

logml.ai

LOGML 2025

London Geometry and Machine Learning Summer School, July 7-11 2025

2209

Reposted by Valentina Giunchiglia

LOGML Summer School @logml.bsky.social · 11/03/2025

The organisation and scientific advisory committees: @simofoti.bsky.social, @valegiunca.bsky.social, @pragya-singh.bsky.social, @daniel-platt.bsky.social, Vincenzo Marco De Luca, Massimiliano Esposito, Arne Wolf, Zhengang Zhong, Rahul Singh

142

Valentina Giunchiglia @valegiunca.bsky.social · 02/02/2025

Apply by the 16th February! If you have any specific questions, contact: logml.committee@gmail.com

logml.ai

LOGML 2025

London Geometry and Machine Learning Summer School, July 7-11 2025

010

Valentina Giunchiglia @valegiunca.bsky.social · 02/02/2025

We are currently recruiting mentors to lead up to 6 students on a week-long project at the intersection of geometry and ML. Mentors can be PhD students (not first years), Postdocs or lectures! Many projects result in top conferences and journal publications. Mentors expenses will be covered.

logml.ai

LOGML 2025

London Geometry and Machine Learning Summer School, July 7-11 2025

110

Valentina Giunchiglia @valegiunca.bsky.social · 02/02/2025

LOGML (London Geometry and Machine Learning) summer school is back and we are looking for mentors! @logml.bsky.social aims to bring together mathematicians and computer scientists to collaborate on problems at the intersection of geometry and ML. More information is available at www.logml.ai.

logml.ai

LOGML 2025

London Geometry and Machine Learning Summer School, July 7-11 2025

121

Reposted by Valentina Giunchiglia

LOGML Summer School @logml.bsky.social · 22/01/2025

⭐️Mentor applications open⭐️ We're excited to announce that LOGML summer school will return in London: July 7-11 2025. We are seeking mentors to lead group projects at the intersection of geometry and machine learning. Find out more and apply: logml.ai

1136

Reposted by Valentina Giunchiglia

AI x Bio Discovery @aixbiobot.bsky.social · 16/12/2024

ProCyon: A multimodal foundation model for protein phenotypes [new]

031

Reposted by Valentina Giunchiglia

bioRxivpreprint @biorxivpreprint.bsky.social · 16/12/2024

ProCyon: A multimodal foundation model for protein phenotypes www.biorxiv.org/content/10.1101/202…

011

Valentina Giunchiglia @valegiunca.bsky.social · 24/12/2024

I am happy to finally share ProCyon, a multimodal multiscale model that integrates protein sequences, structures, and natural language to predict and generate protein phenotypes. Paper: www.biorxiv.org/content/10.1... Blog post: kempnerinstitute.harvard.edu/research/dee...

100

Reposted by Valentina Giunchiglia

Stephen Turner @stephenturner.us · 18/12/2024

ProCyon: A multimodal foundation model for protein phenotypes www.biorxiv.org/content/10.1101/202… 🧬🖥️🧪 github.com/mims-harvard/ProCyon

041

Valentina Giunchiglia @valegiunca.bsky.social · 13/12/2024

We tested it on 12 online tasks collected with Cognitron. Compared to standard measures of RT and accuracy, IDoCT's measures of ability: - have more interpretable latent cognitive factors - are less sensitive to device - have higher sensitivity and specificity

100

Valentina Giunchiglia @valegiunca.bsky.social · 13/12/2024

We tested the model on simulated data and IDoCT could reliably recover ground truth measures of trial’s difficulty, ability and visuomotor delay

100

Valentina Giunchiglia @valegiunca.bsky.social · 13/12/2024

IDoCT comes with a nice set of features: - Robust: Works with as little as 100 participants - Efficient: Scales up inexpensively to > 100K participants - Flexible: Can work with potentially any online task collecting trial-by-trial responses

100

Valentina Giunchiglia @valegiunca.bsky.social · 13/12/2024

IDoCT derives specific estimates of ability, and visuomotor delay from trial-by-trial measures of reaction time (RT) and accuracy, while also providing data-driven trial’s difficulty scales that detect the most challenging aspects/dimensions of each task

100

Valentina Giunchiglia @valegiunca.bsky.social · 13/12/2024

🚨 It took two years but it finally happened! Excited to share IDoCT - a novel computational model that can disentangle the motor and cognitive component from participants’ performance in online cognitive tasks - now published in Nature Digital Medicine.

110