Zobrazeno 1 - 10
of 656
pro vyhledávání: '"WU Xiao-ming"'
Autor:
WU Wen-fu, Wuyunshandan, CHEN Kai, CUI Hong-wei, ZHANG Zhong-jie, YIN Jun, XU Qi-keng, WU Xiao-ming
Publikováno v:
Liang you shipin ke-ji, Vol 31, Iss 2, Pp 11-17 (2023)
The supervision of grain reserves is a major event of national food security. China has built the largest grain internet of things in the world. Although there are still have some problems such as low data quality, low utilization rate, and serious i
Externí odkaz:
https://doaj.org/article/ed1fa97f6625455a9baaa0be73756b5e
For 6-DoF grasp detection, simulated data is expandable to train more powerful model, but it faces the challenge of the large gap between simulation and real world. Previous works bridge this gap with a sim-to-real way. However, this way explicitly o
Externí odkaz:
http://arxiv.org/abs/2410.06521
Cognitive biases are systematic deviations in thinking that lead to irrational judgments and problematic decision-making, extensively studied across various fields. Recently, large language models (LLMs) have shown advanced understanding capabilities
Externí odkaz:
http://arxiv.org/abs/2409.16022
Autor:
Liu, Bo, Zhan, Liming, Feng, Yujie, Lu, Zexin, Xie, Chengqiang, Xue, Lei, Lam, Albert Y. S., Wu, Xiao-Ming
In the realm of task-oriented dialogue systems, a robust intent detection mechanism must effectively handle malformed utterances encountered in real-world scenarios. This study presents a novel fine-tuning framework for large language models (LLMs) a
Externí odkaz:
http://arxiv.org/abs/2409.11114
Traditional recommendation models often rely on unique item identifiers (IDs) to distinguish between items, which can hinder their ability to effectively leverage item content information and generalize to long-tail or cold-start items. Recently, sem
Externí odkaz:
http://arxiv.org/abs/2409.07276
The fashion domain encompasses a variety of real-world multimodal tasks, including multimodal retrieval and multimodal generation. The rapid advancements in artificial intelligence generated content, particularly in technologies like large language m
Externí odkaz:
http://arxiv.org/abs/2408.11305
A practical dialogue system requires the capacity for ongoing skill acquisition and adaptability to new tasks while preserving prior knowledge. However, current methods for Continual Dialogue State Tracking (DST), a crucial function of dialogue syste
Externí odkaz:
http://arxiv.org/abs/2408.09857
Autor:
Feng, Yujie, Liu, Bo, Dong, Xiaoyu, Lu, Zexin, Zhan, Li-Ming, Lam, Albert Y. S., Wu, Xiao-Ming
An ideal dialogue system requires continuous skill acquisition and adaptation to new tasks while retaining prior knowledge. Dialogue State Tracking (DST), vital in these systems, often involves learning new services and confronting catastrophic forge
Externí odkaz:
http://arxiv.org/abs/2408.09846
Online person re-identification services face privacy breaches from potential data leakage and recovery attacks, exposing cloud-stored images to malicious attackers and triggering public concern. The privacy protection of pedestrian images is crucial
Externí odkaz:
http://arxiv.org/abs/2408.05543
Language model continual learning (CL) has recently attracted significant interest for its ability to adapt large language models (LLMs) to dynamic real-world scenarios without retraining. A major challenge in this domain is catastrophic forgetting,
Externí odkaz:
http://arxiv.org/abs/2408.05200