8 accepted papers
Computational pathology has advanced rapidly in recent years, driven by domain-specific image encoders and growing interest in using vision-language models to answer natural-language questions about diseases. Yet, the core problem behind pathology question-answering remains unsolved, considering tha
Versatile 3D tasks (e.g., generation or editing) distilling Text-to-Image (T2I) diffusion models have attracted significant research interest for not relying on extensive 3D training data. However, T2I models exhibit limitations resulting from prior view bias, which produces conflicting appearances
Soft growing robots, as highly mobile pneumatic membrane robots, are limited in control performance due to their soft structure and nonlinear mechanical properties, especially under dynamic conditions. Therefore, developing reliable control strategies for the robot is essential. This study proposes …
Keyframe selection has become essential for video understanding with vision-language models (VLMs) due to limited input tokens and the temporal sparsity of relevant information across video frames. Video understanding often relies on effective keyframes that are not only informative but also causall
Soft growing robots, as highly mobile pneumatic membrane robots, are limited in control performance due to their soft structure and nonlinear mechanical properties, especially under dynamic conditions. Therefore, developing reliable control strategies for the robot is essential. This study proposes
Recent advances in Spatial Transcriptomics (ST) pair histology images with spatially resolved gene expression profiles, enabling predictions of gene expression across different tissue locations based on image patches. This opens up new possibilities for enhancing whole slide image (WSI) prediction t…
Magnetic microrobots are potentially used in various biomedical applications due to their distinguished properties in bio-related manipulation such as minimally invasive and accessible in complex bio-environment. Precise path tracking control of magnetic microrobots in complex interference is an imp
A framework is presented for unsupervised learning of representations based on infomax principle for large-scale neural populations. We use an asymptotic approximation to the Shannon's mutual information for a large neural population to demonstrate that a good initial approximation to the global inf…