← Search

Bo Hong

5 accepted papers

2026

FloorPlanFormer: Multi-Task Transformer Network for Floor Plan Recognition with Outer-to-Inner Feature Refinement

AAAI 2026technical

Floor plan recognition requires accurate segmentation and classification of entrance doors, outer contours (walls and windows) and inner contours (various room types) , despite strong spatial dependencies and large stylistic differences between different datasets. To overcome these challenges, we pr

Cited by 0SourcePDFScholar
2026

Hippoformer: Integrating Hippocampus-inspired Spatial Memory with Transformers

ICLR 2026poster

Transformers form the foundation of modern generative AI, yet their key–value memory lacks inherent spatial priors, constraining their capacity for spatial reasoning. In contrast, neuroscience points to the hippocampal–entorhinal system, where the medial entorhinal cortex provides structural codes a…

Cited by 0SourcecodeScholar
2024

Leveraging Attractor Dynamics in Spatial Navigation for Better Language Parsing

ICML 2024spotlight

Increasing experimental evidence suggests that the human hippocampus, evolutionarily shaped by spatial navigation tasks, also plays an important role in language comprehension, indicating a shared computational mechanism for both functions. However, the specific relationship between the hippocampal…

Cited by 0SourcePDFScholar
2023

Learning and processing the ordinal information of temporal sequences in recurrent neural circuits

NeurIPS 2023poster

Temporal sequence processing is fundamental in brain cognitive functions. Experimental data has indicated that the representations of ordinal information and contents of temporal sequences are disentangled in the brain, but the neural mechanism underlying this disentanglement remains largely unclea…

Cited by 0SourcePDFScholar