Center for Advanced Intelligence Project

**Date: November 25, 2025 (JST)**
**Format: In-person**
**Venue: Seminar Room A/D (3th floor), Faculty of Engineering Building 6, University of Tokyo**

(This is a pre-open-workshop of AIVP, RIKEN-AIP & A*STAR Joint Workshop)

Program

14:00–14:30: Yan Shuo Tan (NUS) (invited talk)
Sparse modeling revisited: From linear models to LLMs
14:30–15:00: Shaoli Wang (Shanghai University of Finance and Economics)
High-dimensional differentially private quantile regression: distributed estimation and statistical inference
15:00–15:30: Wei Huang (RIKEN-AIP)
Trained Mamba Emulates Online Gradient Descent in In-Context Linear Regression
15:30–16:00 Coffee break
16:00–16:30: Razvan-Andrei Lascu (RIKEN-AIP)
Proximal Policy Optimization in the Fisher-Rao geometry
16:30–17:00: Chongxiao Wang (A*STAR)
Transporting Distributions: From Density Ratios to Deterministic Sampling

Organizer: Taiji Suzuki (University of Tokyo / Deep Learning Theory Team, RIKEN-AIP)
Sponsored by AI Visiting Professorship Programme (AIVP-2024-004)