Zobrazeno 1 - 10
of 26
pro vyhledávání: '"Wan, Zhongwei"'
Recent advances show that two-stream approaches have achieved outstanding performance in hateful meme detection. However, hateful memes constantly evolve as new memes emerge by fusing progressive cultural ideas, making existing methods obsolete or in
Externí odkaz:
http://arxiv.org/abs/2407.21004
Autor:
Tao, Chaofan, Liu, Qian, Dou, Longxu, Muennighoff, Niklas, Wan, Zhongwei, Luo, Ping, Lin, Min, Wong, Ngai
Research on scaling large language models (LLMs) has primarily focused on model parameters and training data size, overlooking the role of vocabulary size. We investigate how vocabulary size impacts LLM scaling laws by training models ranging from 33
Externí odkaz:
http://arxiv.org/abs/2407.13623
Autor:
Wan, Zhongwei, Wu, Ziang, Liu, Che, Huang, Jinfa, Zhu, Zhihong, Jin, Peng, Wang, Longyue, Yuan, Li
Long-context Multimodal Large Language Models (MLLMs) demand substantial computational resources for inference as the growth of their multimodal Key-Value (KV) cache, in response to increasing input lengths, challenges memory and time efficiency. Unl
Externí odkaz:
http://arxiv.org/abs/2406.18139
Autor:
Wan, Zhongwei, Wu, Xinjian, Zhang, Yu, Xin, Yi, Tao, Chaofan, Zhu, Zhihong, Wang, Xin, Luo, Siqi, Xiong, Jing, Zhang, Mi
Efficient inference in Large Language Models (LLMs) is impeded by the growing memory demands of key-value (KV) caching, especially for longer sequences. Traditional KV cache eviction strategies, which prioritize less critical KV-pairs based on attent
Externí odkaz:
http://arxiv.org/abs/2406.13035
Autor:
Liu, Che, Wan, Zhongwei, Wang, Yuqi, Shen, Hui, Wang, Haozhe, Zheng, Kangyu, Zhang, Mi, Arcucci, Rossella
Automatic radiology report generation can significantly benefit the labor-intensive process of report writing by radiologists, especially for 3D radiographs like CT scans, which are crucial for broad clinical diagnostics yet underexplored compared to
Externí odkaz:
http://arxiv.org/abs/2406.07146
Autor:
Zheng, Kangyu, Lu, Yingzhou, Zhang, Zaixi, Wan, Zhongwei, Ma, Yao, Zitnik, Marinka, Fu, Tianfan
Currently, the field of structure-based drug design is dominated by three main types of algorithms: search-based algorithms, deep generative models, and reinforcement learning. While existing works have typically focused on comparing models within a
Externí odkaz:
http://arxiv.org/abs/2406.03403
The advancements in Large Language Models (LLMs) have been hindered by their substantial sizes, which necessitate LLM compression methods for practical deployment. Singular Value Decomposition (SVD) offers a promising solution for LLM compression. Ho
Externí odkaz:
http://arxiv.org/abs/2403.07378
Electrocardiograms (ECGs) are non-invasive diagnostic tools crucial for detecting cardiac arrhythmic diseases in clinical practice. While ECG Self-supervised Learning (eSSL) methods show promise in representation learning from unannotated ECG data, t
Externí odkaz:
http://arxiv.org/abs/2403.06659
Autor:
Wan, Zhongwei, Liu, Che, Wang, Xin, Tao, Chaofan, Shen, Hui, Peng, Zhenwu, Fu, Jie, Arcucci, Rossella, Yao, Huaxiu, Zhang, Mi
Electrocardiogram (ECG) is the primary non-invasive diagnostic tool for monitoring cardiac conditions and is crucial in assisting clinicians. Recent studies have concentrated on classifying cardiac conditions using ECG data but have overlooked ECG re
Externí odkaz:
http://arxiv.org/abs/2403.04945
Autor:
Wang, Xin, Wan, Zhongwei, Hekmati, Arvin, Zong, Mingyu, Alam, Samiul, Zhang, Mi, Krishnamachari, Bhaskar
Equipped with sensing, networking, and computing capabilities, Internet of Things (IoT) such as smartphones, wearables, smart speakers, and household robots have been seamlessly weaved into our daily lives. Recent advancements in Generative AI exempl
Externí odkaz:
http://arxiv.org/abs/2401.01923