CVPR-ICML Pre-Conference by Sydney AI Meetup

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.

Please register in advance to help us plan catering accordingly.

Venue: Lecture Theatre 123, Level 1 School of Computer Science (J12)

1 Cleveland St, Darlington NSW 2008

Zoom link: https://uni-sydney.zoom.us/j/89104469419?from=addon

8:50-9:00

Opening remark

9:00-10:30 Session 1 (6 papers)

Yuankai Qi (Macquarie University)

Question-guided Visual Compression with Memory Feedback for Long-Term Video Understanding

Xiangyu Zeng (University of Sydney)

HiCI: Hierarchical Construction–Integration for Long-Context Attention

Haodong Lu (University of New South Wales)

Little by Little: Continual Learning via Incremental Mixture of Rank-1 Associative Memory Experts

Xiangpeng Yang (University of Technology Sydney)

Unified Video Editing as Temporal Reasoner

Ky Dan Nguyen (University of Sydney)

Rethinking Visual Autoregressive Sampling with Information-Grounding Guidance

Ziyi Zhao (University of Technology Sydney)

BrainStack: Neuro-MoE with Functionally Guided Expert Routing for EEG-Based Language Decoding

10:30-11:00 Morning tea break

11:00-12:45 Session 2 (7 papers)

Huan Wang (University of Wollongong) [online]

Domain-Skewed Federated Learning with Feature Decoupling and Calibration

Huan Wang (University of Wollongong) [online]

FedHPro: Federated Hyper-Prototype Learning via Gradient Matching

Shutong Chen (University of Technology Sydney)

Personalized Additive Modeling for Multi-level Federated Learning

Chongyang Zhao (University of New South Wales)

On Token’s Dilemma: Dynamic MoE with Drift-Aware Token Assignment for Continual Learning of Large Vision Language Models

ChengCheng Wang (University of Sydney)

Circle-RoPE: Cone-like Decoupled Rotary Positional Embedding for Vision-Language Models

Chunlei Zhang (University of Technology Sydney)

Disentangle-then-Align: Non-Iterative Hybrid Multimodal Image Registration via Cross-Scale Feature Disentanglement

Yunxiao Shi (University of Technology Sydney)

AgentSelect: Benchmark for Narrative Query-to-Agent Recommendation

12:45 - 14:00 Lunch break

14:00-15:30 Session 3 (6 papers)

Yang Xiao (University of Technology Sydney)

CoverPruneGS: Coverage-Preserving Structured Pruning for Hierarchical 3D Gaussian Splatting from Sparse-View Monocular Videos

Enhuai Liu (University of Sydney)

D2Cache: Second-Order Delta Caching for Higher Video Diffusion Acceleration

Yu Zhang (Macquarie University)

XTransfer: Modality-Agnostic Few-Shot Model Transfer for Human Sensing at the Edge

Yutong Wang (University of Sydney)

VDOT: Efficient Unified Video Creation via Optimal Transport Distillation

Yunyi Liu (University of Sydney)

SAT-RRG: LLM-Guided Self-Adaptive Training for Radiology Report Generation with Token-Level Push–Pull Optimization

Zhuoli Zhuang (University of Technology Sydney)

Neuro-Cognitive Reward Modeling for Human-Centered Autonomous Vehicle Control

15:30-15:40 Closing remark

Event Venue & Nearby Stays

Lecture Theatre 123, Level 1 School of Computer Science (J12) 1 Cleveland St, Darlington NSW 2008, Lecture Theatre 123, Building J12/1 Cleveland St, Sydney, Australia

Concerts, fests, parties, meetups - all the happenings, one place.

Get App