Zobrazeno 1 - 10
of 802
pro vyhledávání: '"Zhang, WenXuan"'
Fine-tuning large language models (LLMs) on human preferences, typically through reinforcement learning from human feedback (RLHF), has proven successful in enhancing their capabilities. However, ensuring the safety of LLMs during the fine-tuning rem
Externí odkaz:
http://arxiv.org/abs/2408.15313
SeaLLMs 3: Open Foundation and Chat Multilingual Large Language Models for Southeast Asian Languages
Autor:
Zhang, Wenxuan, Chan, Hou Pong, Zhao, Yiran, Aljunied, Mahani, Wang, Jianyu, Liu, Chaoqun, Deng, Yue, Hu, Zhiqiang, Xu, Weiwen, Chia, Yew Ken, Li, Xin, Bing, Lidong
Large Language Models (LLMs) have shown remarkable abilities across various tasks, yet their development has predominantly centered on high-resource languages like English and Chinese, leaving low-resource languages underserved. To address this dispa
Externí odkaz:
http://arxiv.org/abs/2407.19672
In recent years, the neural-network quantum states method has been investigated to study the ground state and the time evolution of many-body quantum systems. Here we expand on the investigation and consider a quantum quench from the paramagnetic to
Externí odkaz:
http://arxiv.org/abs/2406.03381
As LLMs evolve on a daily basis, there is an urgent need for a trustworthy evaluation method that can provide robust evaluation results in a timely fashion. Currently, as static benchmarks are prone to contamination concerns, users tend to trust huma
Externí odkaz:
http://arxiv.org/abs/2405.20267
Autor:
Zhang, Wenxuan, Mohamed, Youssef, Ghanem, Bernard, Torr, Philip H. S., Bibi, Adel, Elhoseiny, Mohamed
We propose and study a realistic Continual Learning (CL) setting where learning algorithms are granted a restricted computational budget per time step while training. We apply this setting to large-scale semi-supervised Continual Learning scenarios w
Externí odkaz:
http://arxiv.org/abs/2404.12766
Large language models (LLMs) have demonstrated multilingual capabilities; yet, they are mostly English-centric due to the imbalanced training corpora. Existing works leverage this phenomenon to improve their multilingual performances through translat
Externí odkaz:
http://arxiv.org/abs/2403.10258
As an effective alternative to the direct fine-tuning on target tasks in specific languages, cross-lingual transfer addresses the challenges of limited training data by decoupling ''task ability'' and ''language ability'' by fine-tuning on the target
Externí odkaz:
http://arxiv.org/abs/2402.18913
Large language models (LLMs) have demonstrated impressive capabilities across diverse languages. This study explores how LLMs handle multilingualism. Based on observed language ratio shifts among layers and the relationships between network structure
Externí odkaz:
http://arxiv.org/abs/2402.18815
Web agents powered by Large Language Models (LLMs) have demonstrated remarkable abilities in planning and executing multi-step interactions within complex web-based environments, fulfilling a wide range of web navigation tasks. Despite these advancem
Externí odkaz:
http://arxiv.org/abs/2402.15057
Autor:
Schuessler, Christian, Zhang, Wenxuan, Bräunig, Johanna, Hoffmann, Marcel, Stelzig, Michael, Vossiek, Martin
In the fast-paced field of human-computer interaction (HCI) and virtual reality (VR), automatic gesture recognition has become increasingly essential. This is particularly true for the recognition of hand signs, providing an intuitive way to effortle
Externí odkaz:
http://arxiv.org/abs/2402.12800