← Search

Zhijia Liang

2 accepted papers

2026

OASIS: On-Demand Hierarchical Event Memory for Streaming Video Reasoning

CVPR 2026

Streaming video reasoning requires models to operate in a setting where history grows without bound while meaningful evidence remains scarce. In such a landscape, relevant signal is like an oasis -- small, critical, and easily lost in a desert of redundancy. Enlarging memory only widens the desert;

Cited by 0SourcecodeScholar
2025

GUIDED: Granular Understanding via Identification, Detection, and Discrimination for Fine-Grained Open-Vocabulary Object Detection

NeurIPS 2025poster

Fine-grained open-vocabulary object detection (FG-OVD) aims to detect novel object categories described by attribute-rich texts. While existing open-vocabulary detectors show promise at the base-category level, they underperform in fine-grained settings due to the semantic entanglement of subjects a…

Cited by 0SourceScholar