Kento Masui

Shunki Uebayashi, Kento Masui, Kyohei Atarashi et al.

Multimodal Large Language Models (MLLMs) have recently emerged as general architectures capable of reasoning over diverse modalities. Benchmarks for MLLMs should measure their ability for cross-modal integration. However, current benchmarks are filled with shortcut questions, which can be solved using only a single modality, thereby yielding unreliable rankings. For example, in vision-language cases, we can find the correct answer without either the image or the text. These low-quality questions unnecessarily increase the size and computational requirements of benchmarks. We introduce a multi-modal and multidimensional item response theory framework (M3IRT) that extends classical IRT by decomposing both model ability and item difficulty into image-only, text-only, and cross-modal components. M3IRT estimates cross-modal ability of MLLMs and each question's cross-modal difficulty, enabling compact, high-quality subsets that better reflect multimodal reasoning. Across 24 VLMs on three benchmarks, M3IRT prioritizes genuinely cross-modal questions over shortcuts and preserves ranking fidelity even when 50% of items are artificially generated low-quality questions, thereby reducing evaluation cost while improving reliability. M3IRT thus offers a practical tool for assessing cross-modal reasoning and refining multimodal benchmarks.

Julian Jorge Andrade Guerreiro, Naoto Inoue, Kento Masui et al.

Finding a suitable layout represents a crucial task for diverse applications in graphic design. Motivated by simpler and smoother sampling trajectories, we explore the use of Flow Matching as an alternative to current diffusion-based layout generation models. Specifically, we propose LayoutFlow, an efficient flow-based model capable of generating high-quality layouts. Instead of progressively denoising the elements of a noisy layout, our method learns to gradually move, or flow, the elements of an initial sample until it reaches its final prediction. In addition, we employ a conditioning scheme that allows us to handle various generation tasks with varying degrees of conditioning with a single model. Empirically, LayoutFlow performs on par with state-of-the-art models while being significantly faster.

Qianru Qiu, Jiafeng Mao, Kento Masui et al.

Recent advances in diffusion models have significantly improved the performance of reference-guided line art colorization. However, existing methods still struggle with region-level color consistency, especially when the reference and target images differ in character pose or motion. Instead of relying on external matching annotations between the reference and target, we propose to discover semantic correspondences implicitly through internal attention mechanisms. In this paper, we present MangaDiT, a powerful model for reference-guided line art colorization based on Diffusion Transformers (DiT). Our model takes both line art and reference images as conditional inputs and introduces a hierarchical attention mechanism with a dynamic attention weighting strategy. This mechanism augments the vanilla attention with an additional context-aware path that leverages pooled spatial features, effectively expanding the model's receptive field and enhancing region-level color alignment. Experiments on two benchmark datasets demonstrate that our method significantly outperforms state-of-the-art approaches, achieving superior performance in both qualitative and quantitative evaluations.

Naoto Inoue, Kento Masui, Wataru Shimoda et al.

Automatic generation of graphic designs has recently received considerable attention. However, the state-of-the-art approaches are complex and rely on proprietary datasets, which creates reproducibility barriers. In this paper, we propose an open framework for automatic graphic design called OpenCOLE, where we build a modified version of the pioneering COLE and train our model exclusively on publicly available datasets. Based on GPT4V evaluations, our model shows promising performance comparable to the original COLE. We release the pipeline and training results to encourage open development.