← Search

Zhaoze Wang

5 accepted papers

2025

REMI: Reconstructing Episodic Memory During Internally Driven Path Planning

NeurIPS 2025poster

Grid cells in the medial entorhinal cortex (MEC) and place cells in the hippocampus (HC) both form spatial representations. Grid cells fire in triangular grid patterns, while place cells fire at specific locations and respond to contextual cues. How do these interacting systems support not only spat…

Cited by 0SourceScholar
2024

Cross-Modal Supervision Based Road Segmentation and Trajectory Prediction With Automotive Radar

RA-L 2024

Automotive radar plays a crucial role in providing reliable environmental perception for autonomous driving, particularly in challenging conditions such as high speeds and bad weather. In this domain the deep learning-based method is one of the most promising approaches, but the presence of noisy si

Cited by 3SourceScholar
2024

Time Makes Space: Emergence of Place Fields in Networks Encoding Temporally Continuous Sensory Experiences

NeurIPS 2024poster

The vertebrate hippocampus is thought to use recurrent connectivity in area CA3 to support episodic memory recall from partial cues. This brain area also contains place cells, whose location-selective firing fields implement maps supporting spatial memory. Here we show that place cells emerge in net…

Cited by 3SourcePDFScholar
2024

Trading Place for Space: Increasing Location Resolution Reduces Contextual Capacity in Hippocampal Codes

NeurIPS 2024oral

Many animals learn cognitive maps of their environment - a simultaneous representation of context, experience, and position. Place cells in the hippocampus, named for their explicit encoding of position, are believed to be a neural substrate of these maps, with place cell "remapping" explaining how…

Cited by 0SourcePDFScholar
2022

Cross-Patch Dense Contrastive Learning for Semi-Supervised Segmentation of Cellular Nuclei in Histopathologic Images

CVPR 2022poster

We study the semi-supervised learning problem, using a few labeled data and a large amount of unlabeled data to train the network, by developing a cross-patch dense contrastive learning framework, to segment cellular nuclei in histopathologic images. This task is motivated by the expensive burden on…

Cited by 90PDFcodeScholar