Sydney AI Meetup
CVPR · ICML Pre-Conference 2026
Friday, 22 May 2026
University of Sydney · J12 LT 123
University of Sydney · J12 LT 123
A focused seminar sharing and discussing the latest breakthrough papers from top-tier machine learning and computer vision conferences.
Join us for a dynamic research sharing session spotlighting cutting-edge papers from CVPR 2026 and ICML 2026. This event brings together rising researchers from universities across the greater Sydney area to present and discuss their latest contributions in machine learning and computer vision. It offers a unique opportunity to engage with the vibrant local research community.
Free to attend — please register in advance to help us plan catering.
Friday, 22 May 2026
9:00 AM – 3:30 PM (Sydney)
Join the Sydney AI Meetup Community for the latest event updates, discussion, and networking.
Please register in advance to help us plan catering.
| 8:30 – 9:00 | Registration & coffee | |
| 9:00 – 10:30 | Session 1 | |
| Paper 1 | Question-guided Visual Compression with Memory Feedback for Long-Term Video Understanding | Yuankai Qi Macquarie University |
| Paper 2 | HiCI: Hierarchical Construction–Integration for Long-Context Attention | Xiangyu Zeng University of Sydney |
| Paper 3 | Little by Little: Continual Learning via Incremental Mixture of Rank-1 Associative Memory Experts | Haodong Lu UNSW |
| Paper 4 | Unified Video Editing as Temporal Reasoner | Xiangpeng Yang University of Technology Sydney |
| Paper 5 | Rethinking Visual Autoregressive Sampling with Information-Grounding Guidance | Ky Dan Nguyen University of Sydney |
| Paper 6 | BrainStack: Neuro-MoE with Functionally Guided Expert Routing for EEG-Based Language Decoding | Ziyi Zhao University of Technology Sydney |
| 10:30 – 11:00 | Morning tea | |
| 11:00 – 12:30 | Session 2 | |
| Paper 7 | Domain-Skewed Federated Learning with Feature Decoupling and Calibration | Huan Wang (online) University of Wollongong |
| Paper 8 | FedHPro: Federated Hyper-Prototype Learning via Gradient Matching | Huan Wang (online) University of Wollongong |
| Paper 9 | Personalized Additive Modeling for Multi-level Federated Learning | Shutong Chen University of Technology Sydney |
| Paper 10 | On Token's Dilemma: Dynamic MoE with Drift-Aware Token Assignment for Continual Learning of Large Vision Language Models | Chongyang Zhao UNSW |
| Paper 11 | Circle-RoPE: Cone-like Decoupled Rotary Positional Embedding for Vision-Language Models | ChengCheng Wang University of Sydney |
| Paper 12 | Disentangle-then-Align: Non-Iterative Hybrid Multimodal Image Registration via Cross-Scale Feature Disentanglement | Chunlei Zhang University of Technology Sydney |
| 12:30 – 14:00 | Lunch break | |
| 14:00 – 15:30 | Session 3 | |
| Paper 13 | CoverPruneGS: Coverage-Preserving Structured Pruning for Hierarchical 3D Gaussian Splatting from Sparse-View Monocular Videos | Yang Xiao University of Technology Sydney |
| Paper 14 | D2Cache: Second-Order Delta Caching for Higher Video Diffusion Acceleration | Enhuai Liu University of Sydney |
| Paper 15 | XTransfer: Modality-Agnostic Few-Shot Model Transfer for Human Sensing at the Edge | Yu Zhang Macquarie University |
| Paper 16 | VDOT: Efficient Unified Video Creation via Optimal Transport Distillation | Yutong Wang University of Sydney |
| Paper 17 | SAT-RRG: LLM-Guided Self-Adaptive Training for Radiology Report Generation with Token-Level Push–Pull Optimization | Yunyi Liu University of Sydney |
| Paper 18 | Neuro-Cognitive Reward Modeling for Human-Centered Autonomous Vehicle Control | Zhuoli Zhuang University of Technology Sydney |
| 15:30 – 15:40 | Closing remarks |
