Associate Professor, The University of Queensland
3 papers at NeurIPS 2025
an efficient model merging approach for online adapting lidar-based 3D detection and end-to-end autonomous driving systems
A novel vision-language pretraining method that explores ordering and continuity of videos for robot manipulation
We propose LFlow, a training-free framework for solving linear inverse problems using pretrained latent flow priors with theoretically grounded posterior guidance, achieving superior reconstruction quality over latent diffusion baselines.
