Papers by Shuhei Tateishi
Word-Aware Modality Stimulation for Multimodal Fusion (2024.lrec-main)
Copied to clipboard
| Challenge: | Multimodal learning is expected to make more accurate predictions than text-only analysis. |
| Approach: | They propose a method for fusing multimodal inputs with text-based fusion methods . they propose fusion that integrates non-verbal modalities with text . |
| Outcome: | The proposed method improves sentiment prediction by using non-verbal modalities with text . the proposed method is unsuitable for applying attention to text modality in the fusion phase . |
ACT: Knowledgeable Agents to Design and Perform Complex Tasks (2025.acl-long)
Copied to clipboard
Makoto Nakatsuji, Shuhei Tateishi, Yasuhiro Fujiwara, Ayaka Matsumoto, Narichika Nomoto, Yoshihide Sato
| Challenge: | Large language models (LLMs) have rapidly evolved and become pervasive in everyday human life. |
| Approach: | They propose a method called knowledgeable Agents to design and perform Complex Tasks where agents independently manage their knowledge and tasks while collaboratively design the complex task into a more comprehensible form. |
| Outcome: | The proposed method outperforms existing methods in solving complex tasks. |