[2025] UQ AI Conference Dry Run Seminar Series

(Part of EECS Data Science Discipline HDR Student Support)

📍 Date & Time: October 13, 2025, 1:00–4:00 PM

📍 Location: 46-402 Seminar/Board Room (Andrew Liveris Building)

🧑‍💼 Panel Members:

Session I: Prof Shazia Sadiq, Prof Ryan Ko, Dr Ruihong Qiu

Session II: Dr Joel Mackenzie, A/Prof Mahsa Baktashmotlagh, Dr Alina Bialkowski

☕ Tea Break and Networking: 2:20-2:40 PM

<aside> 💡

About the Event…

The UQ AI Conference Dry Run Seminar Series is an initiative launched by the UQ EECS Data Science Discipline to support our HDR student community. This inaugural event marks the beginning of a recurring seminar series designed to help our students shine on the global stage.

The goals of the series are to:

Practice presentations: Give HDR students the chance to rehearse their talks for top international conferences
Receive constructive feedback: Present in a supportive environment and gain insights from peers and faculty that can sharpen delivery and content.
Showcase UQ research: Share cutting-edge work with a broader audience, raising the visibility of the exciting contributions coming from UQ.
Build community: Strengthen connections across research groups and foster collaboration through shared discussion and networking.

Format: 10-minute presentation + 5-minute Q&A session

This series will serve as a training ground for students preparing to present at major venues, while also offering the UQ community a front-row seat to the innovative AI research being developed within our faculty.

</aside>

📅 UQ AI Dry Run Seminar Schedule

Time	Speaker	Title	Group	Venue
1:00–1:15	Zixin Wang	Is Less More? Exploring Token Condensation as Training-free Test-time Adaptation	🔵 Test-time Adaptation & Embodied AI	ICCV
1:15–1:30	Zhizhen Zhang	Provable Ordering and Continuity in Vision-Language Pretraining for Generalizable Embodied Agents	🔵 Test-time Adaptation & Embodied AI	NeurIPS
1:30–1:45	Bingqing Zhang	Quantifying and Narrowing the Unknown: Interactive Text-to-Video Retrieval via Uncertainty Minimization	🟢 Video Understanding & Retrieval	ICCV
1:45–2:00	Zhuo Cao	When One Moment Isn’t Enough: Multi-Moment Retrieval with Cross-Moment Interactions	🟢 Video Understanding & Retrieval	NeurIPS
2:00–2:15	Zecheng Zhao	Are Synthetic Videos Useful? A Benchmark for Retrieval-Centric Evaluation of Synthetic Videos	🟢 Video Understanding & Retrieval	MM
2:15–2:40	🧑‍💼 Panel Members	🏅Best Student Talk – Part I (Awarding Session #1) and ☕ Tea Break Networking	⚪ Social
2:40–2:55	Bowen Yuan	WisWheat: A Three-Tiered Vision-Language Dataset for Wheat Management	🟣 Domain-specific VL Models & Datasets	MM
2:55–3:10	Xiaobiao Du	3DRealCar: An In-the-wild RGB-D Car Dataset with 360-degree Views	🟣 Domain-specific VL Models & Datasets	ICCV
3:10–3:25	Jiaying Ying	LDPose: Towards Inclusive Human Pose Estimation for Limb-Deficient Individuals in the Wild	🟠 Human-Centric AI	ICCV
3:25–3:40	Hossein Askari	Latent Refinement via Flow Matching for Training-free Linear Inverse Problem Solving	🔴 Theory & Inference	NeurIPS
3:45–4:00	🧑‍💼 Panel Members	🏅Best Student Talk – Part II (Awarding Session #2)	⚪ Social

Talk Information

Untitled