Zobrazeno 1 - 10
of 211
pro vyhledávání: '"YU, Haofei"'
Recent advancements in artificial intelligence have led to the creation of highly capable large language models (LLMs) that can perform tasks in a human-like manner. However, LLMs exhibit only infant-level cognitive abilities in certain areas. One su
Externí odkaz:
http://arxiv.org/abs/2409.15454
Autor:
Liang, Paul Pu, Goindani, Akshay, Chafekar, Talha, Mathur, Leena, Yu, Haofei, Salakhutdinov, Ruslan, Morency, Louis-Philippe
Multimodal foundation models that can holistically process text alongside images, video, audio, and other sensory modalities are increasingly used in a variety of real-world applications. However, it is challenging to characterize and study progress
Externí odkaz:
http://arxiv.org/abs/2407.03418
Autor:
Wang, Ruiyi, Yu, Haofei, Zhang, Wenxin, Qi, Zhengyang, Sap, Maarten, Neubig, Graham, Bisk, Yonatan, Zhu, Hao
Humans learn social skills through both imitation and social interaction. This social learning process is largely understudied by existing research on building language agents. Motivated by this gap, we propose an interactive learning method, SOTOPIA
Externí odkaz:
http://arxiv.org/abs/2403.08715
Autor:
Yu, Haofei, Qi, Zhengyang, Jang, Lawrence, Salakhutdinov, Ruslan, Morency, Louis-Philippe, Liang, Paul Pu
Advances in multimodal models have greatly improved how interactions relevant to various tasks are modeled. Today's multimodal models mainly focus on the correspondence between images and text, using this for tasks like image-text matching. However,
Externí odkaz:
http://arxiv.org/abs/2311.09580
The Transformer architecture is crucial for numerous AI models, but it still faces challenges in long-range language modeling. Though several specific transformer architectures have been designed to tackle issues of long-range dependencies, existing
Externí odkaz:
http://arxiv.org/abs/2310.15494
Autor:
Weissweiler, Leonie, Hofmann, Valentin, Kantharuban, Anjali, Cai, Anna, Dutt, Ritam, Hengle, Amey, Kabra, Anubha, Kulkarni, Atharva, Vijayakumar, Abhishek, Yu, Haofei, Schütze, Hinrich, Oflazer, Kemal, Mortensen, David R.
Large language models (LLMs) have recently reached an impressive level of linguistic capability, prompting comparisons with human language skills. However, there have been relatively few systematic inquiries into the linguistic capabilities of the la
Externí odkaz:
http://arxiv.org/abs/2310.15113
Autor:
Zhou, Xuhui, Zhu, Hao, Mathur, Leena, Zhang, Ruohong, Yu, Haofei, Qi, Zhengyang, Morency, Louis-Philippe, Bisk, Yonatan, Fried, Daniel, Neubig, Graham, Sap, Maarten
Humans are social beings; we pursue social goals in our daily interactions, which is a crucial aspect of social intelligence. Yet, AI systems' abilities in this realm remain elusive. We present SOTOPIA, an open-ended environment to simulate complex s
Externí odkaz:
http://arxiv.org/abs/2310.11667
Open-Domain Question Answering (ODQA) systems necessitate a reader model capable of generating answers by simultaneously referring to multiple passages. Although representative models like Fusion-in-Decoder (FiD) have been proposed to address this ch
Externí odkaz:
http://arxiv.org/abs/2305.17041
Autor:
Huang, Banglian, Lei, Feifei, Yu, Haofei, Chen, Xinglong, Hu, Weiyan, Hou, Bo, Zhang, Rongping
Publikováno v:
In Fitoterapia September 2024 177
Sample-and-rank is a key decoding strategy for modern generation-based dialogue systems. It helps achieve diverse and high-quality responses by selecting an answer from a small pool of generated candidates. The current state-of-the-art ranking method
Externí odkaz:
http://arxiv.org/abs/2106.01263