Zobrazeno 1 - 10
of 241
pro vyhledávání: '"Cui, Yufei"'
Real-time object detection is critical for the decision-making process for many real-world applications, such as collision avoidance and path planning in autonomous driving. This work presents an innovative real-time streaming perception method, Tran
Externí odkaz:
http://arxiv.org/abs/2409.06584
Autor:
Wu, Shangyu, Xiong, Ying, Cui, Yufei, Wu, Haolun, Chen, Can, Yuan, Ye, Huang, Lianming, Liu, Xue, Kuo, Tei-Wei, Guan, Nan, Xue, Chun Jason
Large language models (LLMs) have demonstrated great success in various fields, benefiting from their huge amount of parameters that store knowledge. However, LLMs still suffer from several key issues, such as hallucination problems, knowledge update
Externí odkaz:
http://arxiv.org/abs/2407.13193
Autor:
Huang, Lianming, Wu, Shangyu, Cui, Yufei, Xiong, Ying, Liu, Xue, Kuo, Tei-Wei, Guan, Nan, Xue, Chun Jason
Deploying large language model inference remains challenging due to their high computational overhead. Early exiting optimizes model inference by adaptively reducing the number of inference layers. Existing methods typically train internal classifier
Externí odkaz:
http://arxiv.org/abs/2405.15198
Autor:
Zhou, Hao, Hu, Chengming, Yuan, Ye, Cui, Yufei, Jin, Yili, Chen, Can, Wu, Haolun, Yuan, Dun, Jiang, Li, Wu, Di, Liu, Xue, Zhang, Charlie, Wang, Xianbin, Liu, Jiangchuan
Large language models (LLMs) have received considerable attention recently due to their outstanding comprehension and reasoning capabilities, leading to great progress in many fields. The advancement of LLM techniques also offers promising opportunit
Externí odkaz:
http://arxiv.org/abs/2405.10825
In safety-critical applications such as medical imaging and autonomous driving, where decisions have profound implications for patient health and road safety, it is imperative to maintain both high adversarial robustness to protect against potential
Externí odkaz:
http://arxiv.org/abs/2405.08886
Immunohistochemistry (IHC) plays a crucial role in pathology as it detects the over-expression of protein in tissue samples. However, there are still fewer machine learning model studies on IHC's impact on accurate cancer grading. We discovered that
Externí odkaz:
http://arxiv.org/abs/2405.08197
Pre-processing whole slide images (WSIs) can impact classification performance. Our study shows that using fixed hyper-parameters for pre-processing out-of-domain WSIs can significantly degrade performance. Therefore, it is critical to search domain-
Externí odkaz:
http://arxiv.org/abs/2404.11161
Retrieval-based augmentations (RA) incorporating knowledge from an external database into language models have greatly succeeded in various knowledge-intensive (KI) tasks. However, integrating retrievals in non-knowledge-intensive (NKI) tasks is stil
Externí odkaz:
http://arxiv.org/abs/2401.02993
Recent works on learned index open a new direction for the indexing field. The key insight of the learned index is to approximate the mapping between keys and positions with piece-wise linear functions. Such methods require partitioning key space for
Externí odkaz:
http://arxiv.org/abs/2205.11807
Deep-learning-based compressor has received interests recently due to much improved compression ratio. However, modern approaches suffer from long execution time. To ease this problem, this paper targets on cutting down the execution time of deep-lea
Externí odkaz:
http://arxiv.org/abs/2203.16114