Zobrazeno 1 - 10
of 1 184
pro vyhledávání: '"Wang, WenXuan"'
Autor:
Liu, Xiaoyuan, Wang, Wenxuan, Yuan, Youliang, Huang, Jen-tse, Liu, Qiuzhi, He, Pinjia, Tu, Zhaopeng
This paper explores the problem of commonsense-level vision-knowledge conflict in Multimodal Large Language Models (MLLMs), where visual information contradicts model's internal commonsense knowledge (see Figure 1). To study this issue, we introduce
Externí odkaz:
http://arxiv.org/abs/2410.08145
Autor:
Wang, Wenxuan, Gao, Kuiyi, Jia, Zihan, Yuan, Youliang, Huang, Jen-tse, Liu, Qiuzhi, Wang, Shuai, Jiao, Wenxiang, Tu, Zhaopeng
Text-based image generation models, such as Stable Diffusion and DALL-E 3, hold significant potential in content creation and publishing workflows, making them the focus in recent years. Despite their remarkable capability to generate diverse and viv
Externí odkaz:
http://arxiv.org/abs/2410.03869
In this paper, we establish strong holomorphic Morse inequalities on non-compact manifolds under the condition of optimal fundamental estimates. We show that optimal fundamental estimates are satisfied and then strong holomorphic Morse inequalities h
Externí odkaz:
http://arxiv.org/abs/2409.16836
Autor:
Wang, Chaozheng, Gao, Shuzheng, Gao, Cuiyun, Wang, Wenxuan, Chong, Chun Yong, Gao, Shan, Lyu, Michael R.
API suggestion is a critical task in modern software development, assisting programmers by predicting and recommending third-party APIs based on the current context. Recent advancements in large code models (LCMs) have shown promise in the API sugges
Externí odkaz:
http://arxiv.org/abs/2409.13178
Autor:
Wang, Wenxuan, Shi, Juluan, Wang, Chaozheng, Lee, Cheryl, Yuan, Youliang, Huang, Jen-tse, Lyu, Michael R.
Equipped with the capability to call functions, modern large language models (LLMs) can leverage external tools for addressing a range of tasks unattainable through language skills alone. However, the effective execution of these tools relies heavily
Externí odkaz:
http://arxiv.org/abs/2409.00557
Autor:
Wang, Wenxuan
Large language models (LLMs), such as ChatGPT, have rapidly penetrated into people's work and daily lives over the past few years, due to their extraordinary conversational skills and intelligence. ChatGPT has become the fastest-growing software in t
Externí odkaz:
http://arxiv.org/abs/2409.00551
Autor:
Feng, Zuo, Wang, Wenxuan, You, Yilong, Chen, Yifei, Watanabe, Kenji, Taniguchi, Takashi, Liu, Chang, Liu, Kaihui, Lu, Xiaobo
The extrinsic stacking sequence based on intrinsic crystal symmetry in multilayer two-dimensional materials plays a significant role in determining their electronic and optical properties. Compared with Bernal-stacked (ABA) multilayer graphene, rhomb
Externí odkaz:
http://arxiv.org/abs/2408.09814
Autor:
Huang, Jen-tse, Zhou, Jiaxu, Jin, Tailin, Zhou, Xuhui, Chen, Zixi, Wang, Wenxuan, Yuan, Youliang, Sap, Maarten, Lyu, Michael R.
Multi-agent systems, powered by large language models, have shown great abilities across various tasks due to the collaboration of expert agents, each focusing on a specific domain. However, when agents are deployed separately, there is a risk that m
Externí odkaz:
http://arxiv.org/abs/2408.00989
Contrastive Language-Image Pre-training (CLIP), which excels at abstracting open-world representations across domains and modalities, has become a foundation for a variety of vision and multimodal tasks. However, recent studies reveal that CLIP has s
Externí odkaz:
http://arxiv.org/abs/2407.20171
Autor:
Yuan, Youliang, Jiao, Wenxiang, Wang, Wenxuan, Huang, Jen-tse, Xu, Jiahao, Liang, Tian, He, Pinjia, Tu, Zhaopeng
This study addresses a critical gap in safety tuning practices for Large Language Models (LLMs) by identifying and tackling a refusal position bias within safety tuning data, which compromises the models' ability to appropriately refuse generating un
Externí odkaz:
http://arxiv.org/abs/2407.09121