3 papers
cs.CV2023
Pointing out Human Answer Mistakes in a Goal-Oriented Visual Dialogue
Ryosuke Oshima, Seitaro Shinagawa, Hideki Tsunashima +2
Effective communication between humans and intelligent agents has promising applications for solving complex problems. One such approach is visual dialogue, which leverages multimo…
cs.CV2023
Memory Efficient Diffusion Probabilistic Models via Patch-based Generation
Shinei Arakawa, Hideki Tsunashima, Daichi Horita +2
Diffusion probabilistic models have been successful in generating high-quality and diverse images. However, traditional models, whose input and output are high-resolution images, s…
cond-mat.mtrl-sci2023
Enhancing Inverse Problem Solutions with Accurate Surrogate Simulators and Promising Candidates
Akihiro Fujii, Hideki Tsunashima, Yoshihiro Fukuhara +2
Deep-learning inverse techniques have attracted significant attention in recent years. Among them, the neural adjoint (NA) method, which employs a neural network surrogate simulato…