Venue: Computer Science Building (J12) Board Room (J12.01.124) (Google Map) at the University of Sydney, 5 Dec 2026.
WIFI to UniSydney-Guest, Username: sydney_riken; Password: sydriken11
Zoom Link: https://uni-sydney.zoom.us/j/7891224702
Sydney - RIKEN AIP Joint AI Workshop
Overview
The AI community is developing very fast. Efficient and effective communication is essential for exchanging ideas, building collaborations, and conducting impactful research, etc. This regional workshop aims to bring together some AI researchers to facilitate communication. In this workshop, we propose to showcase a variety of recent advances from presenters, with three emphases, i.e., (1) exchanging ideas; (2) inspiring the juniors to do better research; (3) promoting potential collaborations.
Program
5 Dec 2026 (Sydney time)
| 09:15-09:30am | Welcome and opening remarks |
| 09:30-09:50am | Speaker: Qibin Zhao Title: Structured Representation and Learning: Tensor Network Principles for Efficient and Reliable AI |
| 09:50-10:10am | Speaker: Thomas Humphries Title: PE-Means: Improved Differentially Private k-means Clustering through Private Evolution |
| 10:10-10:30am | Speaker: Taira Tsuchiya Title: Muon with Finite Newton–Schulz: The Smoothing Benefit in Nonsmooth Nonconvex Optimization |
| 10:30-11:00am | Tea break | 11:00-11:20am | Speaker: Zhen Fang Title: TBD |
11:20-11:40am | Speaker: Zhen-Yu Zhang Title: Learning-to-reweight Rollouts: Mitigating Distribution Shift in Group Relative Policy Optimization |
11:40-12:00pm | Speaker: Sichao Li Title: Chain-of-Thought Oversight Requires Separate Evidence for Faithfulness and Monitorability |
12:00-14:30pm | Lunch and poster session Light lunch will be provided onsite |
14:30-14:50pm | Speaker: Hong Jin Kang Title: Interpretable and Debuggable Agentic Vulnerability Analysis |
14:50-15:10pm | Speaker: Taoli Zheng Title: Last-Iterate Convergence of Single-Loop Stochastic Methods for Constrained Convex-Concave Minimax Problems |
15:10-15:30pm | Speaker: Anusha Withana Title: TBD |
15:30-16:00pm | Tea break | 16:00-16:20pm | Speaker: Bo Han Title: Trustworthy ML Systems for Deep Agentic Reasoning and Evaluating Open Agents |
16:20-16:40pm | Speaker: Jiyang Zheng Title: Beyond Text-to-Video: Towards Agentic Video Creation and Self-Improvement |
16:40-17:00pm | Speaker: Noboru Isobe Title: Training-Induced Escape from Token Clustering in a Mean-Field Formulation of Transformers |
| 17:00-17:05pm | Closing remarks | |
Workshop Co-chairs
A/Prof Tongliang Liu; University of Sydney
Dr Sichao Li; University of Sydney
Prof Masashi Sugiyama; RIKEN / University of Tokyo
Sponsors
