Zhiyuan Han — accepted AI-conference papers

2026

Omni-Perception Policy Optimization for Multimodal Emotion Reasoning

Zhiyuan Han, Beier Zhu, Wenwen Tong, Pengyang Shao, Peipei Song, Xinyi Wang +3

ICML 2026poster

Recent Omni-MLLMs are driving a paradigm shift in multimodal emotion recognition from label-only prediction toward *Multimodal Emotion Reasoning* (MER), where models output both emotions and textual explanations grounded in visual, acoustic, and linguistic signals. However, we show that current emot…

Cited by 0 Source ↗Scholar ↗

2025

AugRefer: Advancing 3D Visual Grounding via Cross-Modal Augmentation and Spatial Relation-based Referring

Xinyi Wang, Na Zhao, Zhiyuan Han, Dan Guo, Xun Yang

AAAI 2025technical

3D visual grounding (3DVG), which aims to correlate a natural language description with the target object within a 3D scene, is a significant yet challenging task. Despite recent advancements in this domain, existing approaches commonly encounter a shortage: a limited amount and diversity of text-3D…

Cited by 1 Source ↗PDF ↗Scholar ↗