- University of Chinese Academy of SciencesCN5 papers
- Chinese Academy of SciencesCN4 papers
- Hangzhou Dianzi UniversityCN2 papers
- China Academy of Safety Sciences and TechnologyCN1 paper
- Dartmouth CollegeUS1 paper
- Dartmouth HospitalGB1 paper
- Georgia Institute of TechnologyUS1 paper
- Inner Mongolia University of TechnologyCN1 paper
- Institute for Mobile and Satellite Communication TechnologyDE1 paper
- Leibniz University HannoverDE1 paper
- Lishui UniversityCN1 paper
- Ludong UniversityCN1 paper
10 papers
DishSeg24k: A Large-Scale Benchmark for Food Segmentation with Stochastic Expert Decoding
Yilin Wang, Haochen Shi, Guanyu Chen +4
Food segmentation is essential for applications such as intelligent catering, dietary assessment, and recommendation. However, existing benchmarks fail to capture the complexity of…
Scalable and Culturally Specific Stereotype Dataset Construction via Human-LLM Collaboration
Weicheng Ma, John Guerrerio, Soroush Vosoughi
Research on stereotypes in large language models (LLMs) has largely focused on English-speaking contexts, due to the lack of datasets in other languages and the high cost of manual…
From Prediction to Intervention: Personalized Meal-Level Glucose Regulation via an LLM Agent
Mingyu Huang, Weiqing Min, Ying Jin +2
Personalized glucose regulation remains a central yet unresolved challenge in precision nutrition, as postprandial glucose response varies substantially across individuals. Existin…
RFHNet: Relational and Frequency-Aware Hashing Network for Large-Scale Fine-Grained Food Image Retrieval
Junsong Wang, Weiqing Min, Guorui Sheng +3
Fine-grained food image retrieval is a key task in computational gastronomy, with applications in food traceability, dietary monitoring, and smart catering systems. Although hashin…
Towards Mitigation of Hallucination for LLM-empowered Agents: Progressive Generalization Bound Exploration and Watchdog Monitor
Siyuan Liu, Wenjing Liu, Zhiwei Xu +3
Empowered by large language models (LLMs), intelligent agents have become a popular paradigm for interacting with open environments to facilitate AI deployment. However, hallucinat…
BE Lyncis: A Pulsating Star in the Most Eccentric Binary with a Massive Unseen Companion
Jia-Shu Niu, Ying Zhang, Hui-Fang Xue
We report the discovery of an exceptionally eccentric binary system, BE Lyncis (BE Lyn), which might host a compact companion with mass . By combining TESS p…