We have gathered a high-quality corpus of millions of sentiment-labeled data points from real users and trained a LLM using the Transformer methodology, achieving human-like sentiment input and output. Our models are built with a MoE architecture and are available in two specifications: 8*7B and 8*3B.
AvatarPop is a virtual social product driven by AI, where users can chat with over 10 million interesting virtual characters, fostering new-generation social connections. AI friends are available 24/7, transcending time and space.
Provides an API for emotion computation and sentiment recognition. The API's response speed can reach up to 63 tokens per second and supports long texts up to 128k context. It supports English, Japanese, and Chinese languages and utilizes RAG technology.
use the multi-head attention based bi-directional GRU component and speaker embeddings. Experimental results on the IEMOCAP and MELD datasets demonstrate the effectiveness of the proposed method.
the multi-head attention produces multimodal emotional intermediate representations from common semantic feature space after encoding audio and visual modalities.
new studies are detailing the more nuanced and complex processes involved in emotion recognition and the structure of how people perceive emotional expression.
a holds a Ph.D. from the University of Tokyo and a Master's degree from the University of Waterloo. He has worked at companies such as Oracle Corporation, Samsung R&D Institute, and Tencent Technology. He has extensive experience in areas such as large language models, application develop and more.
Ph.D. in Computer Science from the University of Toronto, serves as a senior researcher. He has been working on computer vision and deep neural network research since 2010, with extensive research and implementation experience in large model tokenization, pre-training, fine-tuning, and engineering.
Ph.D. in Psychology, Associate Professor, Department of Psychology, Graduate School of Humanities and Sociology, The University of Tokyo, Research interests lie in experimental psychology and cognitive psychology, with a primary focus on human cognitive processing, particularly the association between language processing and emotions.
Previously worked at Shanda Network, Joyy Inc., Tencent Technology, and other companies, leading the development of the world's first game community battle product WeGame. Possesses in-depth understanding of community and social products, with skills covering product development, operations, promotion, and more.
