Manuscript | Zongyan Han https://hanzy1996.github.io/publication_types/manuscript/ Manuscript HugoBlox Kit (https://hugoblox.com)en-usSat, 03 Oct 2026 00:00:00 +0000 https://hanzy1996.github.io/media/icon.svg Manuscript https://hanzy1996.github.io/publication_types/manuscript/ AgroGround: Multi-Granularity Grounded Recognition in Agriculture https://hanzy1996.github.io/publications/agroground-multi-granularity-grounded-recognition-in-agriculture/ Sat, 03 Oct 2026 00:00:00 +0000 https://hanzy1996.github.io/publications/agroground-multi-granularity-grounded-recognition-in-agriculture/ <p><a href="https://arxiv.org/abs/2610.04425" target="_blank" rel="noopener">Read the preprint</a></p> Gaussian-JEPA: Joint-Embedding Predictive Learning for 3D Gaussian Splats https://hanzy1996.github.io/publications/gaussian-jepa-joint-embedding-predictive-learning-for-3d-gaussian-splats/ Sun, 16 Aug 2026 00:00:00 +0000 https://hanzy1996.github.io/publications/gaussian-jepa-joint-embedding-predictive-learning-for-3d-gaussian-splats/ <p><a href="https://arxiv.org/abs/2608.15651" target="_blank" rel="noopener">Read the preprint</a></p> Audit After Segmentation: Reference-Free Mask Quality Assessment for Language-Referred Audio-Visual Segmentation https://hanzy1996.github.io/publications/audit-after-segmentation-reference-free-mask-quality-assessment-for-language-referred-audi/ Tue, 03 Feb 2026 00:00:00 +0000 https://hanzy1996.github.io/publications/audit-after-segmentation-reference-free-mask-quality-assessment-for-language-referred-audi/ <p><a href="https://arxiv.org/abs/2602.03892" target="_blank" rel="noopener">Read the preprint</a></p> Composed Object Retrieval: Object-level Retrieval via Composed Expressions https://hanzy1996.github.io/publications/composed-object-retrieval-object-level-retrieval-via-composed-expressions/ Wed, 06 Aug 2025 00:00:00 +0000 https://hanzy1996.github.io/publications/composed-object-retrieval-object-level-retrieval-via-composed-expressions/ <p><a href="https://arxiv.org/abs/2508.04424" target="_blank" rel="noopener">Read the preprint</a></p> OpenSeg-R: Improving Open-Vocabulary Segmentation via Step-by-Step Visual Reasoning https://hanzy1996.github.io/publications/openseg-r-improving-open-vocabulary-segmentation-via-step-by-step-visual-reasoning/ Thu, 22 May 2025 00:00:00 +0000 https://hanzy1996.github.io/publications/openseg-r-improving-open-vocabulary-segmentation-via-step-by-step-visual-reasoning/ <p><a href="https://arxiv.org/abs/2505.16974" target="_blank" rel="noopener">Read the preprint</a></p>