4 papers
Visual Jigsaw Post-Training Improves MLLMs
Penghao Wu, Yushan Zhang, Haiwen Diao +3
Reinforcement learning based post-training has recently emerged as a powerful paradigm for enhancing the alignment and reasoning capabilities of multimodal large language models (M…
Zero-Shot 4D Lidar Panoptic Segmentation
Yushan Zhang, Aljoša Ošep, Laura Leal-Taixé +1
Zero-shot 4D segmentation and recognition of arbitrary objects in Lidar is crucial for embodied navigation, with applications ranging from streaming perception to semantic mapping…
Revisiting the hyperfine interval for the state in Be
Yu-Shan Zhang, Wei Dang, Kai Wang +1
Using relativistic multiconfiguration Dirac-Hartree-Fock method, we calculate the hyperfine-structure properties of the state in Be. The hyperfine-structure…
Flow-guided Semi-supervised Video Object Segmentation
Yushan Zhang, Andreas Robinson, Maria Magnusson +1
We propose an optical flow-guided approach for semi-supervised video object segmentation. Optical flow is usually exploited as additional guidance information in unsupervised video…