Program (tentative)

December 18th, 2025 • Wohl Conventions Center, Bar-Ilan University

08:30 - 09:00
Registration & Coffee ☕
09:00 - 09:15
Opening Remarks
Yanai Elazar (Bar-Ilan University) & Avi Caciularu (Google)
09:15 - 10:15
Oral Session A
Chair: Roy Schwartz
DOVE: A Large-Scale Multi-Dimensional Predictions Dataset Towards Meaningful LLM Evaluation
Eliya Habba, Ofir Arviv, Itay Itzhak, Yotam Perlitz, Elron Bandel, Leshem Choshen, Michal Shmueli-Scheuer, Gabriel Stanovsky
Same Task, Different Circuits: Disentangling Modality-Specific Mechanisms in VLMs
Yaniv Nikankin, Dana Arad, Yossi Gandelsman, Yonatan Belinkov
Confidence Improves Self-Consistency in LLMs
Amir Taubenfeld, Tom Sheffer, Eran Ofek, Amir Feder, Ariel Goldstein, Zorik Gekhman, Gal Yona
Humans Perceive Wrong Narratives from AI Reasoning Texts
Mosh Levy, Zohar Elyoseph, Yoav Goldberg
10:15 - 11:15
Posters Session 1 + Coffee ☕
11:15 - 12:15
Keynote Talk | Prof. Dan Roth (University of Pennsylvania, Oracle)
Title: TBD | Chair: Ido Dagan
12:15 - 12:45
A Memorial Session for Prof. Ari Rappoport
12:45 - 13:45
Lunch 🍽️
13:45 - 14:45
Posters Session 2 + Coffee ☕
14:45 - 15:30
Panel Discussion | The future of AI Tools in AI research and education
Chair: Ella Rabinovich
Panelists: Giora Alexandron, Yoav Goldberg, Gili Lior
15:30 - 16:30
Oral Session B
Chair: Yuval Pinter
Preventing Rogue Agents Improves Multi Agent Collaboration
Ohav Barbi, Ori Yoran, Mor Geva
Guided Query Refinement: Multimodal Hybrid Retrieval with Test-Time Optimization
Omri Uzan, Asaf Yehudai, Roi Pony, Eyal Shnarch, Ariel Gera
The Value of Nothing: Multimodal Extraction of Human Values Expressed by TikTok Influencers
Alon Neduva, Alina Starovolsky-Shitrit, Naama Appel Doron, Ella Daniel, Oren Tsur
MATCH: Task-Driven Code Evaluation through Contrastive Learning
Marah Ghoummaid, Vladimir Tchuiev, Ofek Glick, Michal Moshkovitz, Dotan Di Castro
16:30 - 16:40
Closing remarks & Candle Lighting
TBD
16:40 - 17:40
Posters Session 3 + Sufganiyot