arXiv subjects

Kazuki Hayashi

Publications and source records attributed to Kazuki Hayashi.

18 recordsLinked to original sources

arXiv2026

Michell-Prager type truss structures constructed from integrable discrete power function and discrete logarithmic function

The Michell-Prager type truss structures are constructed from the integrable discrete power and logarithmic functions. It is demonstrated that specific sublattices, subject to suitable boundary conditions, yield approximate Michell trusses, which are theoretically optimal structures achieving force equilibrium with material economy. The result of shape optimization minimizing the Michell functional is provided for numerical evidence of their optimality.

math.DG↗

arXiv2026

ExpArt-KG: Artwork Image Description Generation through Iterative Exploration of Knowledge Graphs

Large Vision-Language Models (LVLMs) achieve strong performance on image-grounded text generation and visual question answering. However, it remains difficult for them to comprehensively and accurately describe the factual relations among the entities and concepts associated with the objects depicted in an image. In this work, we propose a framework that efficiently exploits factual information from a knowledge graph via retrieval-augmented generation (RAG), with the goal of enabling LVLMs to generate detailed and accurate image explanations. Specifically, our method alternates between answer generation and knowledge-graph retrieval, and controls the search using a correctness judgment, thereby acquiring the necessary and sufficient factual information efficiently. We also construct a knowledge graph for the artwork domain (ExpArt-KG), in which the correspondence between images and entities is unambiguous. Applying the proposed method to this knowledge graph, we show experimentally that it improves the level of detail of artwork explanations and reduces the retrieval cost of external knowledge while maintaining generation quality comparable to that of iterating a fixed number of times.

cs.CL↗

arXiv2026

A characterization of perfectoid towers in terms of conormal cones

We characterize perfectoid towers in terms of conormal cones rather than torsion parts. This result is deduced from a refined study of the relationship between torsion with respect to a principal ideal and the associated conormal cone, building on the work of O. Gabber and L. Ramero.

math.AC↗

arXiv2026

Structural properties and tilting correspondences of perfectoid towers

We prove that every perfectoid tower can be realized as the fiber product of a diagram involving perfectoid towers that are either $p$-torsion free or perfect of characteristic $p$. As an application, we conclude that separated perfectoid towers are reduced. We also establish the tilting invariance of Koszul homology for perfectoid towers. As further applications, we prove that tilting preserves fundamental properties of Noetherian local rings such as being Cohen--Macaulay, Gorenstein, complete intersection, or regular.

math.AC↗

arXiv2026

Regular rings and perfectoid towers

We prove a mixed-characteristic analogue of Kunz's theorem in terms of perfectoid towers: a Noetherian local ring of residue characteristic $p$ is regular if and only if it admits a flat map to a Noetherian ring that extends to a perfectoid tower. This result is deduced from another mixed-characteristic analogue due to O. Gabber and J. Lurie. We also characterize regularity for perfectoid towers via vanishing of single higher $\mathrm{Tor}$-module of the residue field with a perfectoid algebra.

math.AC↗

arXiv2026

TextTIGER: Text-based Intelligent Generation with Entity Prompt Refinement for Text-to-Image Generation

When generating images from prompts that include specific entities, the model must retain as much entity-specific knowledge as possible. However, the number of entities is almost countless, and new entities emerge; memorizing all of them completely is not realistic. To bridge this gap, our work proposes Text-based Intelligent Generation with Entity Prompt Refinement (TextTIGER). TextTIGER strengthens knowledge about entities that appear in the prompt by augmenting external information and then summarizes the expanded descriptions with large language models, preventing performance degradation that arises from excessively long inputs. To evaluate our method, we construct a new dataset consisting of captions, images, detailed descriptions, and lists of entities. Experiments with multiple image generation models show that TextTIGER improves image generation performance on widely used evaluation metrics compared with prompts that use captions alone. In addition, using Multimodal LLM (MLLM)-as-a-judge, which shows a strong correlation with human evaluation, we demonstrate that our method consistently achieves higher scores, which underscores its effectiveness. These results show that strengthening entity-related descriptions, summarizing them, and refining prompts to an appropriate length leads to substantial improvements in image generation performance. We will release the created dataset and code upon acceptance.

cs.CL↗

arXiv2026

An application of Fontaine's monoidal maps to perfectoid towers

To connect arithmetic and ring-theoretic properties of rings of mixed characteristic with those of positive characteristic, we introduce monoidal maps for perfectoid towers. Using these maps, we discuss the almost integrality of perfectoid towers and of their tilts. We also show that the towers constructed by F. Andreatta via ramification theory become perfectoid towers, and we apply the monoidal maps to deduce the normality of their small tilts.

math.AC↗

arXiv2026

Towards Artwork Explanation in Large-scale Vision Language Models

Large-scale Vision-Language Models (LVLMs) output text from images and instructions, demonstrating capabilities in text generation and comprehension. However, it has not been clarified to what extent LVLMs possess the ability to understand the knowledge necessary for explaining images, the complex relationships between various pieces of knowledge, and how they integrate these understandings into their explanations. To address this issue, we propose a new task: the artwork explanation generation task, along with its evaluation dataset and metrics for quantitatively assessing the understanding and utilization of knowledge about artworks. This task is apt for image description based on the premise that LVLMs are expected to have pre-existing knowledge of artworks, which are often subjects of wide recognition and documented information. It consists of two parts: generating explanations from images and titles of artworks, and generating explanations using only images, thus evaluating the LVLMs' language-based and vision-based knowledge. Alongside, we release a training dataset for LVLMs to learn explanations that incorporate knowledge about artworks. Our findings indicate that LVLMs not only struggle with integrating language and visual information but also exhibit a more pronounced limitation in acquiring knowledge from images alone.

cs.CV↗

arXiv2026

Diagnosing Vision Language Models' Perception by Leveraging Human Methods for Color Vision Deficiencies

Large-scale Vision-Language Models (LVLMs) are being deployed in real-world settings that require visual inference. As capabilities improve, applications in navigation, education, and accessibility are becoming practical. These settings require accommodation of perceptual variation rather than assuming a uniform visual experience. Color perception illustrates this requirement: it is central to visual understanding yet varies across individuals due to Color Vision Deficiencies, an aspect largely ignored in multimodal AI. In this work, we examine whether LVLMs can account for variation in color perception using the Ishihara Test. We evaluate model behavior through generation, confidence, and internal representation, using Ishihara plates as controlled stimuli that expose perceptual differences. Although models possess factual knowledge about color vision deficiencies and can describe the test, they fail to reproduce the perceptual outcomes experienced by affected individuals and instead default to normative color perception. These results indicate that current systems lack mechanisms for representing alternative perceptual experiences, raising concerns for accessibility and inclusive deployment in multimodal settings.

cs.CV↗

arXiv2025

BQA: Body Language Question Answering Dataset for Video Large Language Models

A large part of human communication relies on nonverbal cues such as facial expressions, eye contact, and body language. Unlike language or sign language, such nonverbal communication lacks formal rules, requiring complex reasoning based on commonsense understanding. Enabling current Video Large Language Models (VideoLLMs) to accurately interpret body language is a crucial challenge, as human unconscious actions can easily cause the model to misinterpret their intent. To address this, we propose a dataset, BQA, a body language question answering dataset, to validate whether the model can correctly interpret emotions from short clips of body language comprising 26 emotion labels of videos of body language. We evaluated various VideoLLMs on BQA and revealed that understanding body language is challenging, and our analyses of the wrong answers by VideoLLMs show that certain VideoLLMs made significantly biased answers depending on the age group and ethnicity of the individuals in the video. The dataset is available.

cs.CL↗

arXiv2025

Understanding the Impact of Confidence in Retrieval Augmented Generation: A Case Study in the Medical Domain

Retrieval Augmented Generation (RAG) complements the knowledge of Large Language Models (LLMs) by leveraging external information to enhance response accuracy for queries. This approach is widely applied in several fields by taking its advantage of injecting the most up-to-date information, and researchers are focusing on understanding and improving this aspect to unlock the full potential of RAG in such high-stakes applications. However, despite the potential of RAG to address these needs, the mechanisms behind the confidence levels of its outputs remain underexplored. Our study focuses on the impact of RAG, specifically examining whether RAG improves the confidence of LLM outputs in the medical domain. We conduct this analysis across various configurations and models. We evaluate confidence by treating the model's predicted probability as its output and calculating several evaluation metrics which include calibration error method, entropy, the best probability, and accuracy. Experimental results across multiple datasets confirmed that certain models possess the capability to judge for themselves whether an inserted document relates to the correct answer. These results suggest that evaluating models based on their output probabilities determine whether they function as generators in the RAG framework. Our approach allows us to evaluate whether the models handle retrieved documents.

cs.CL↗

arXiv2025

IterKey: Iterative Keyword Generation with LLMs for Enhanced Retrieval Augmented Generation

Retrieval-Augmented Generation (RAG) has emerged as a way to complement the in-context knowledge of Large Language Models (LLMs) by integrating external documents. However, real-world applications demand not only accuracy but also interpretability. While dense retrieval methods provide high accuracy, they lack interpretability; conversely, sparse retrieval methods offer transparency but often fail to capture the full intent of queries due to their reliance on keyword matching. To address these issues, we introduce IterKey, an LLM-driven iterative keyword generation framework that enhances RAG via sparse retrieval. IterKey consists of three LLM-driven stages: generating keywords for retrieval, generating answers based on retrieved documents, and validating the answers. If validation fails, the process iteratively repeats with refined keywords. Across four QA tasks, experimental results show that IterKey achieves 5% to 20% accuracy improvements over BM25-based RAG and simple baselines. Its performance is comparable to dense retrieval-based RAG and prior iterative query refinement methods using dense models. In summary, IterKey is a novel BM25-based approach leveraging LLMs to iteratively refine RAG, effectively balancing accuracy with interpretability.

cs.CL↗

arXiv2025

Towards Cross-Lingual Explanation of Artwork in Large-scale Vision Language Models

As the performance of Large-scale Vision Language Models (LVLMs) improves, they are increasingly capable of responding in multiple languages, and there is an expectation that the demand for explanations generated by LVLMs will grow. However, pre-training of Vision Encoder and the integrated training of LLMs with Vision Encoder are mainly conducted using English training data, leaving it uncertain whether LVLMs can completely handle their potential when generating explanations in languages other than English. In addition, multilingual QA benchmarks that create datasets using machine translation have cultural differences and biases, remaining issues for use as evaluation tasks. To address these challenges, this study created an extended dataset in multiple languages without relying on machine translation. This dataset that takes into account nuances and country-specific phrases was then used to evaluate the generation explanation abilities of LVLMs. Furthermore, this study examined whether Instruction-Tuning in resource-rich English improves performance in other languages. Our findings indicate that LVLMs perform worse in languages other than English compared to English. In addition, it was observed that LVLMs struggle to effectively manage the knowledge learned from English data. Our dataset is available at https://huggingface.co/datasets/naist-nlp/MultiExpArt

cs.CL↗

arXiv2024

IRR: Image Review Ranking Framework for Evaluating Vision-Language Models

Large-scale Vision-Language Models (LVLMs) process both images and text, excelling in multimodal tasks such as image captioning and description generation. However, while these models excel at generating factual content, their ability to generate and evaluate texts reflecting perspectives on the same image, depending on the context, has not been sufficiently explored. To address this, we propose IRR: Image Review Rank, a novel evaluation framework designed to assess critic review texts from multiple perspectives. IRR evaluates LVLMs by measuring how closely their judgments align with human interpretations. We validate it using a dataset of images from 15 categories, each with five critic review texts and annotated rankings in both English and Japanese, totaling over 2,000 data instances. The datasets are available at https://hf.co/datasets/naist-nlp/Wiki-ImageReview1.0. Our results indicate that, although LVLMs exhibited consistent performance across languages, their correlation with human annotations was insufficient, highlighting the need for further advancements. These findings highlight the limitations of current evaluation methods and the need for approaches that better capture human reasoning in Vision & Language tasks.

cs.CL↗

arXiv2024

Topology optimization of periodic lattice structures for specified mechanical properties using machine learning considering member connectivity

This study proposes a methodology to utilize machine learning (ML) for topology optimization of periodic lattice structures. In particular, we investigate data representation of lattice structures used as input data for ML models to improve the performance of the models, focusing on the filtering process and feature selection. We use the filtering technique to explicitly consider the connectivity of lattice members and perform feature selection to reduce the input data size. In addition, we propose a convolution approach to apply pre-trained models for small structures to structures of larger sizes. The computational cost for obtaining optimal topologies by a heuristic method is reduced by incorporating the prediction of the trained ML model into the optimization process. In the numerical examples, a response prediction model is constructed for a lattice structure of 4x4 units, and topology optimization of 4x4-unit and 8x8-unit structures is performed by simulated annealing assisted by the trained ML model. The example demonstrates that ML models perform higher accuracy by using the filtered data as input than by solely using the data representing the existence of each member. It is also demonstrated that a small-scale prediction model can be constructed with sufficient accuracy by feature selection. Additionally, the proposed method can find the optimal structure in less computation time than the pure simulated annealing.

math.OC↗

arXiv2023

Multiobjective optimization approach to shape and topology optimization of plane trusses with various aspect ratios

A multiobjective optimization method is proposed for obtaining the optimal plane trusses simultaneously for various aspect ratios of the initial ground structure as a set of Pareto optimal solutions generated through a single optimization process. The shape and topology are optimized simultaneously to minimize the compliance under constraint on the total structural volume. The strain energy of each member is divided into components of two coordinate directions on the plane. The force density method is used for alleviating difficulties due to existence of coalescent or melting nodes. It is shown in the numerical example that sufficiently accurate optimal solutions are obtained by comparison with those obtained by the linear weighted sum approach that requires solving a single-objective optimization problem many times.

math.OC↗

arXiv2022

An Independently Learnable Hierarchical Model for Bilateral Control-Based Imitation Learning Applications

Recently, motion generation by machine learning has been actively researched to automate various tasks. Imitation learning is one such method that learns motions from data collected in advance. However, executing long-term tasks remains challenging. Therefore, a novel framework for imitation learning is proposed to solve this problem. The proposed framework comprises upper and lower layers, where the upper layer model, whose timescale is long, and lower layer model, whose timescale is short, can be independently trained. In this model, the upper layer learns long-term task planning, and the lower layer learns motion primitives. The proposed method was experimentally compared to hierarchical RNN-based methods to validate its effectiveness. Consequently, the proposed method showed a success rate equal to or greater than that of conventional methods. In addition, the proposed method required less than 1/20 of the training time compared to conventional methods. Moreover, it succeeded in executing unlearned tasks by reusing the trained lower layer.

cs.RO↗

arXiv2021

A New Autoregressive Neural Network Model with Command Compensation for Imitation Learning Based on Bilateral Control

In the near future, robots are expected to work with humans or operate alone and may replace human workers in various fields such as homes and factories. In a previous study, we proposed bilateral control-based imitation learning that enables robots to utilize force information and operate almost simultaneously with an expert's demonstration. In addition, we recently proposed an autoregressive neural network model (SM2SM) for bilateral control-based imitation learning to obtain long-term inferences. In the SM2SM model, both master and slave states must be input, but the master states are obtained from the previous outputs of the SM2SM model, resulting in destabilized estimation under large environmental variations. Hence, a new autoregressive neural network model (S2SM) is proposed in this study. This model requires only the slave state as input and its outputs are the next slave and master states, thereby improving the task success rates. In addition, a new feedback controller that utilizes the error between the responses and estimates of the slave is proposed, which shows better reproducibility.

cs.RO↗