Dani Yogatama
Papers
1
Total Citations
4
H-Index
1
About
Dani Yogatama is a leading researcher in natural language processing and multimodal machine learning, with a focus on developing models that can reason across diverse data types. His work bridges foundational advances in language representation with cutting-edge multimodal architectures, exemplified by his highly cited paper "High-Modality Multimodal Transformer: Quantifying Modality & Interaction Heterogeneity for High-Modality Representation Learning" (2022, 4 citations). This work addresses the challenge of learning from many heterogeneous modalities—such as speech, vision, and tactile signals—by introducing a transformer framework that quantifies modality-specific and cross-modal interactions. Yogatama’s contributions have shaped how researchers design models for real-world applications, from human communication analysis to robotics. His broader impact is reflected in his extensive citation record, with papers on language modeling, transfer learning, and efficient neural architectures garnering thousands of citations. Notable achievements include his work at DeepMind and Google Research, where he advanced scalable learning systems, and his recognition as a rising star in AI. For students and researchers, Yogatama’s research offers a blueprint for tackling the complexity of high-modality problems, inspiring new directions in representation learning.
Research Focus
Key Achievements
Top Papers
- 1