3 papers
cs.AI2025
Identifying Multi-modal Knowledge Neurons in Pretrained Transformers via Two-stage Filtering
Yugen Sato, Tomohiro Takagi
Recent advances in large language models (LLMs) have led to the development of multimodal LLMs (MLLMs) in the fields of natural language processing (NLP) and computer vision. Altho…
cs.LG2025
RecTable: Fast Modeling Tabular Data with Rectified Flow
Masane Fuchi, Tomohiro Takagi
Score-based or diffusion models generate high-quality tabular data, surpassing GAN-based and VAE-based models. However, these methods require substantial training time. In this pap…
cs.CL2023
Application of frozen large-scale models to multimodal task-oriented dialogue
Tatsuki Kawamoto, Takuma Suzuki, Ko Miyama +2
In this study, we use the existing Large Language Models ENnhanced to See Framework (LENS Framework) to test the feasibility of multimodal task-oriented dialogues. The LENS Framewo…