Zobrazeno 1 - 10
of 104
pro vyhledávání: '"Dong, Chengyu"'
Self-consistency (Wang et al., 2023) suggests that the most consistent answer obtained through large language models (LLMs) is more likely to be correct. In this paper, we challenge this argument and propose a nuanced correction. Our observations ind
Externí odkaz:
http://arxiv.org/abs/2407.05778
For extremely weak-supervised text classification, pioneer research generates pseudo labels by mining texts similar to the class names from the raw corpus, which may end up with very limited or even no samples for the minority classes. Recent works h
Externí odkaz:
http://arxiv.org/abs/2406.11115
Controlling the attribute intensity of text generation is crucial across scenarios (e.g., writing conciseness, chatting emotion, and explanation clarity). The remarkable capabilities of large language models (LLMs) have revolutionized text generation
Externí odkaz:
http://arxiv.org/abs/2406.04460
Autor:
Zhang, Xiyuan, Fu, Xiaohan, Teng, Diyan, Dong, Chengyu, Vijayakumar, Keerthivasan, Zhang, Jiayun, Chowdhury, Ranak Roy, Han, Junsheng, Hong, Dezhi, Kulkarni, Rashmi, Shang, Jingbo, Gupta, Rajesh
Sensors measuring real-life physical processes are ubiquitous in today's interconnected world. These sensors inherently bear noise that often adversely affects performance and reliability of the systems they support. Classic filtering-based approache
Externí odkaz:
http://arxiv.org/abs/2311.06968
ELECTRA pre-trains language models by detecting tokens in a sequence that have been replaced by an auxiliary model. Although ELECTRA offers a significant boost in efficiency, its potential is constrained by the training cost brought by the auxiliary
Externí odkaz:
http://arxiv.org/abs/2310.07347
Autor:
Yan, An, Wang, Yu, Zhong, Yiwu, He, Zexue, Karypis, Petros, Wang, Zihan, Dong, Chengyu, Gentili, Amilcare, Hsu, Chun-Nan, Shang, Jingbo, McAuley, Julian
Medical image classification is a critical problem for healthcare, with the potential to alleviate the workload of doctors and facilitate diagnoses of patients. However, two challenges arise when deploying deep learning models to real-world healthcar
Externí odkaz:
http://arxiv.org/abs/2310.03182
Autor:
Yan, An, Wang, Yu, Zhong, Yiwu, Dong, Chengyu, He, Zexue, Lu, Yujie, Wang, William, Shang, Jingbo, McAuley, Julian
Recent advances in foundation models present new opportunities for interpretable visual recognition -- one can first query Large Language Models (LLMs) to obtain a set of attributes that describe each class, then apply vision-language models to class
Externí odkaz:
http://arxiv.org/abs/2308.03685
Recent advances in weakly supervised text classification mostly focus on designing sophisticated methods to turn high-level human heuristics into quality pseudo-labels. In this paper, we revisit the seed matching-based method, which is arguably the s
Externí odkaz:
http://arxiv.org/abs/2305.14794
Deep neural classifiers trained with cross-entropy loss (CE loss) often suffer from poor calibration, necessitating the task of out-of-distribution (OOD) detection. Traditional supervised OOD detection methods require expensive manual annotation of i
Externí odkaz:
http://arxiv.org/abs/2305.14696
Backpropagation, the cornerstone of deep learning, is limited to computing gradients for continuous variables. This limitation poses challenges for problems involving discrete latent variables. To address this issue, we propose a novel approach to ap
Externí odkaz:
http://arxiv.org/abs/2304.08612