Sunday November 23, 2025 09:00 am - 06:00 pm
S307, New Bund Campus, NYU Shanghai
Schedule for Nov 23, Sunday
Venue: Room S307, NYU Shanghai
- 9:00-9:10 Opening remark
- 9:10-9:45 Stabilization and Optimization with McKean-Vlasov PDEs - Dante Kalise (Imperial College London)
- 9:45-10:20 Transformers - Domènec Ruiz-Balet (Universitat de Barcelona)
- 10:20-10:50 Coffee Break
- 10:50-11:25 Online SFT for LLM Reasoning: Surprising Effectiveness of Self-Tuning without Rewards - Xiao Li (CUHK-Shenzhen)
- 11:25-12:00 Bandit Learning in Metric Spaces via Narrowing - Tianyu Wang (Fudan University)
- 12:00-14:00 Lunch
- 14:00-14:35 Modern Theory of Gradient-Based Optimization - Bin Shi (Fudan University)
- 14:35-15:10 A Unifying Framework for Generalised Bayesian Online Learning in Non-stationary Environments - Alex Shestopaloff (Queen Mary University of London)
- 15:10-15:45 Coffee Break
- 15:45-16:20 Memory Decoder: A Pretrained, Plug-and-Play Memory for Large Language Models - Zhouhan Lin (SJTU)
- 16:20-16:55 Learning Dynamics in the Feature-Learning Regime: Implicit Bias, Neural Collapse and Robustness - Hancheng Min (SJTU)
- 16:55-17:30 Retrieval-based Explainable Multimodal Evidence-guided Modeling for Brain Evaluation and Reasoning in Zero- and Few-shot Neurodegenerative Diagnosis - Thanh Binh Nguyen (Viet Nam National University Ho Chi Minh City)
Schedule for Nov 24, Monday
Venue: Feishu Office, Haina Town Numeral (Digital) Innovation Center
- 14:00-14:35 AI-Powered Plagiarism Detection for Academic Writing: Algorithms, Optimization Challenges, and Real-World Deployment - Sarkhan Talibzadeh (Azerbaijan University of Architecture and Construction)
- 14:35-15:10 Optimal Agnostic Control - Jacob Carruth (Princeton University)
- 15:10-15:45 Applying PatternBoost to the Conductor——Rank Problem for Elliptic Curves - Barinder Banwait (Lodha Mathematical Sciences Institute)
- 15:45-16:15 Break
- 16:15-16:45 Inftychi Project Introduction
- 16:45-17:30 Hackathon Results Announcement and Awards

