Evidence Day
An Innovative Look at the Role of LLMs in Next-Gen Publishing
Agentic interaction with scientific articles is not duct-taping an LLM onto a PDF viewer to produce glorified summaries.
Previous Evidence Day, held in NYU Abu Dhabi, introduced Evidentron.
A lot has changed since last December. LLMs got dramatically better, and they stopped being a novelty in academia. They're now part of how we read, write, and review.
Publishers have noticed and are scrambling to respond. But they're missing the ingredient that matters: the article content as structured data, bundled with its own reproducible sandbox that contains code, data, runtime dependencies, and every relationship between them.That's the difference between a document you can summarize and an object an agent can operate on.
We have the right people to guide this discussion: Stephen Boyd, who made optimization research something you can actually run; Jingang Qu, who builds foundation models that learn directly from tables; and Steve Liu, who builds the computing systems that make any of it affordable.
Plenary Speakers
Scientific Committee
🎨
Themes
CLICK HERE TO REGISTER
The event will take place in Skopje, with participation from our Evidence partners in Canada, Japan, North Macedonia, and UAE.
🇨🇦🇯🇵🇲🇰🇦🇪
Agenda
Plenary talk by Stephen Boyd
🏅 TBD
Samsung Professor in the School of Engineering and Professor of Electrical Engineering at Stanford, where he chairs the EE department. His work is on convex optimization and its applications in control, signal processing, machine learning, and finance. Few researchers have done more to close the gap between a published mathematical result and software that anyone can actually run, and Dr. Boyd is one of them.
Plenary talk by Jingang Qu (remote)
🏅 TBD
Researcher at NVIDIA in Paris, working on AI for graph and structured data. Before NVIDIA he was a postdoctoral researcher in the SODA team at Inria Saclay, and he earned his PhD in machine learning at Sorbonne University (ISIR), where he used deep learning to accelerate numerical simulations. He is the lead author of TabICL, an open tabular foundation model that learns in context from hundreds of thousands of rows and outperforms gradient boosted trees on large tables.
Plenary talk by Xue (Steve) Liu (remote)
🏅 Evidence as an Innovative Platform for AI Research
Professor of Machine Learning and Computer Science at MBZUAI, on leave from McGill University's School of Computer Science. Previously VP R&D and Chief Scientist at Samsung AI Center Montreal, and Chief Scientist at Tinder, with earlier stints at HP Labs and IBM T. J. Watson. IEEE Fellow, Fellow of the Canadian Academy of Engineering, former chair of ACM SIGBED, author of over 400 papers across intelligent computing systems, IoT, cyber physical systems, and sustainable computing.
Coffee Break
Time for a peer-reviewed caffeine intervention. Refuel before the next round of evidence.
Evidence team: Agah Karakuzu
🤖 Agents of the Woven Literature
Agah Karakuzu serves as the principal engineer and technical lead for Evidence, guiding its architecture and development. His talk will explore its newest advances in response to the accelerating pace of AI: the woven literature.
Invited talk: Matthew Akamatsu
🕸️ MIRA: Modular Interoperable Research Attribution
Matthew Akamatsu is an Assistant Professor of Biology at the University of Washington and the 2026–2027 Resident in Open Science at the Astera Institute. His talk will present MIRA.science, a protocol and toolkit that organizes research into an auditable network of claims and evidence to coordinate discoveries between humans and AI agents.
Invited talk: Kiril Gashteovski
⚖️ Peer Review Using AI
Kiril Gashteovski is a Principal Researcher in the Human-Centered AI group at NEC Laboratories Europe, working on natural language processing, knowledge graphs, and explainable AI. His talk will cover what AI reviewers do well and where they fall short, drawing on a study in which 45 expert scientists rated human and AI reviews of Nature-family papers.
Lunch Round Table Discussion (closed session) with Sun Zhe, Bas Rokers, Nikola Stikov, and Ordan Chukaliev
⎈ Evidence Chairs
Over lunch, Sun Zhe (Juntendo University), Bas Rokers (NYU Abu Dhabi), Nikola Stikov (Polytechnique Montreal), and Ordan Chukaliev (UKIM Skopje) will lead a round table discussion on key issues related to Evidence’s long-term success and maintainability.
Evidence Social
🎉 Sponsored by Foundation KANTAROT
Initiating peer-to-peer human networking protocol. No API keys required.
📍 KANTAROT Headquarters, Boul. Ilinden 41, Skopje — view on map
VENUE
FINKI Amphitheatre (A1)
Faculty of Computer Science and Engineering, Ss. Cyril and Methodius University in Skopje
Rugjer Boshkovikj 16, P.O. Box 393, 1000 Skopje, Republic of Macedonia