Wu Kui — accepted AI-conference papers

2026

TrackVLA++: Unleashing Reasoning and Memory Capabilities in VLA Models for Embodied Visual Tracking

Jiahang Liu, Yunpeng Qi, Jiazhao Zhang, Minghan Li, Shaoan Wang, Wu Kui +6

ICRA 2026poster

Embodied Visual Tracking (EVT) is a fundamental ability that underpins practical applications, such as companion robots, guidance robots and service assistants, where continuously following moving targets is essential. Recent advances have enabled language-guided tracking in complex and unstructured…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

CCL-XCoT: An Efficient Cross-Lingual Knowledge Transfer Method for Mitigating Hallucination Generation

Zheng Weihua, Roy Ka-Wei Lee, Zhengyuan Liu, Wu Kui, AiTi Aw, Bowei Zou

EMNLP 2025

Multilingual Large Language Models (MLLMs) demonstrate strong generalization across languages, yet they remain prone to hallucinations, especially in low-resource languages, due to training data imbalances. These hallucinations, which include inaccurate or fabricated outputs, are particularly proble

Cited by 0 Source ↗PDF ↗Scholar ↗