Hiroshi Sasaki

Hiroshi Sasaki

Vision and language models (VLMs) are expected to analyse complex documents, such as those containing flowcharts, through a question-answering (QA) interface. The ability to recognise and interpret these flowcharts is in high demand, as they provide valuable insights unavailable in text-only explanations. However, developing VLMs with precise flowchart understanding requires large-scale datasets of flowchart images and corresponding text, the creation of which is highly time-consuming. To address this challenge, we introduce JSynFlow, a synthesised visual QA dataset for Japanese flowcharts, generated using large language models (LLMs). Our dataset comprises task descriptions for various business occupations, the corresponding flowchart images rendered from domain-specific language (DSL) code, and related QA pairs. This paper details the dataset's synthesis procedure and demonstrates that fine-tuning with JSynFlow significantly improves VLM performance on flowchart-based QA tasks. Our dataset is publicly available at https://huggingface.co/datasets/jri-advtechlab/jsynflow.

Jiuting Chen, Yuan Lian, Hao Wu et al.

We train a 318M-parameter Transformer language model from scratch on a curated corpus of 1.56 billion tokens of pure Classical Chinese, with zero English characters or Arabic numerals. Through systematic out-of-distribution (OOD) testing, we investigate whether the model can distinguish known from unknown inputs, and crucially, whether it can express this distinction in its generated text. We find a clear dissociation between internal and external uncertainty. Internally, the model exhibits a perplexity jump ratio of 2.39x between real and fabricated historical events (p = 8.9e-11, n = 92 per group), with semi-fabricated events (real figures + fictional events) showing the highest perplexity (4.24x, p = 1.1e-16), demonstrating genuine factual encoding beyond syntactic pattern matching. Externally, however, the model never learns to express uncertainty: classical Chinese epistemic markers appear at lower rates for OOD questions (3.5%) than for in-distribution questions (8.3%, p = 0.023), reflecting rhetorical conventions rather than genuine metacognition. We replicate both findings across three languages (Classical Chinese, English, Japanese), three writing systems, and eight models from 110M to 1.56B parameters. We further show that uncertainty expression frequency is determined entirely by training data conventions, with Classical Chinese models showing a "humility paradox" (more hedging for known topics), while Japanese models almost never hedge. We argue that metacognitive expression -- the ability to say "I don't know" -- does not emerge from language modeling alone and requires explicit training signals such as RLHF.

Hiroshi Sasaki

Multimodal models, such as the Contrastive Language-Image Pre-training (CLIP) model, have demonstrated remarkable success in aligning visual and linguistic representations. However, these models exhibit limitations when applied to specialised visual domains, such as diagrams, which encode structured, symbolic information distinct from that of natural imagery. In this paper, we introduce a novel training paradigm explicitly designed to enhance the comprehension of diagrammatic images within vision-language models. Our approach uses ``hard'' samples for our proposed contrastive learning that incorporates two specialised loss functions that leverage the inherent structural properties of diagrams. By integrating these objectives into model training, our method enables models to develop a more structured and semantically coherent understanding of diagrammatic content. We empirically validate our approach on a benchmark dataset of flowcharts, as a representative class of diagrammatic imagery, demonstrating substantial improvements over standard CLIP and conventional hard negative CLIP learning paradigms for both image-text matching and visual question answering tasks. Our findings underscore the significance of tailored training strategies for specialised tasks and contribute to advancing diagrammatic understanding within the broader landscape of vision-language integration.

Sam Bond-Taylor, Peter Hessey, Hiroshi Sasaki et al.

Whilst diffusion probabilistic models can generate high quality image content, key limitations remain in terms of both generating high-resolution imagery and their associated high computational requirements. Recent Vector-Quantized image models have overcome this limitation of image resolution but are prohibitively slow and unidirectional as they generate tokens via element-wise autoregressive sampling from the prior. By contrast, in this paper we propose a novel discrete diffusion probabilistic model prior which enables parallel prediction of Vector-Quantized tokens by using an unconstrained Transformer architecture as the backbone. During training, tokens are randomly masked in an order-agnostic manner and the Transformer learns to predict the original tokens. This parallelism of Vector-Quantized token prediction in turn facilitates unconditional generation of globally consistent high-resolution and diverse imagery at a fraction of the computational expense. In this manner, we can generate image resolutions exceeding that of the original training set samples whilst additionally provisioning per-image likelihood estimates (in a departure from generative adversarial approaches). Our approach achieves state-of-the-art results in terms of Density (LSUN Bedroom: 1.51; LSUN Churches: 1.12; FFHQ: 1.20) and Coverage (LSUN Bedroom: 0.83; LSUN Churches: 0.73; FFHQ: 0.80), and performs competitively on FID (LSUN Bedroom: 3.64; LSUN Churches: 4.07; FFHQ: 6.11) whilst offering advantages in terms of both computation and reduced training set requirements.

Hiroshi Sasaki, Chris G. Willcocks, Toby P. Breckon

We propose a novel unpaired image-to-image translation method that uses denoising diffusion probabilistic models without requiring adversarial training. Our method, UNpaired Image Translation with Denoising Diffusion Probabilistic Models (UNIT-DDPM), trains a generative model to infer the joint distribution of images over both domains as a Markov chain by minimising a denoising score matching objective conditioned on the other domain. In particular, we update both domain translation models simultaneously, and we generate target domain images by a denoising Markov Chain Monte Carlo approach that is conditioned on the input source domain images, based on Langevin dynamics. Our approach provides stable model training for image-to-image translation and generates high-quality image outputs. This enables state-of-the-art Fréchet Inception Distance (FID) performance on several public datasets, including both colour and multispectral imagery, significantly outperforming the contemporary adversarial image-to-image translation methods.

Sachiko Kodera, Akimasa Hirata, Fumiaki Miura et al.

Recent epidemiological studies have hypothesized that the prevalence of cortical cataracts is closely related to ultraviolet radiation. However, the prevalence of nuclear cataracts is higher in elderly people in tropical areas than in temperate areas. The dominant factors inducing nuclear cataracts have been widely debated. In this study, the temperature increase in the lens due to exposure to ambient conditions was computationally quantified in subjects of 50-60 years of age in tropical and temperate areas, accounting for differences in thermoregulation. A thermoregulatory response model was extended to consider elderly people in tropical areas. The time course of lens temperature for different weather conditions in five cities in Asia was computed. The temperature was higher around the mid and posterior part of the lens, which coincides with the position of the nuclear cataract. The duration of higher temperatures in the lens varied, although the daily maximum temperatures were comparable. A strong correlation (adjusted R2 > 0.85) was observed between the prevalence of nuclear cataract and the computed cumulative thermal dose in the lens. We propose the use of a cumulative thermal dose to assess the prevalence of nuclear cataracts. Cumulative wet-bulb globe temperature, a new metric computed from weather data, would be useful for practical assessment in different cities.

Hiroshi Sasaki, Chris G. Willcocks, Toby P. Breckon

Machine learning driven object detection and classification within non-visible imagery has an important role in many fields such as night vision, all-weather surveillance and aviation security. However, such applications often suffer due to the limited quantity and variety of non-visible spectral domain imagery, in contrast to the high data availability of visible-band imagery that readily enables contemporary deep learning driven detection and classification approaches. To address this problem, this paper proposes and evaluates a novel data augmentation approach that leverages the more readily available visible-band imagery via a generative domain transfer model. The model can synthesise large volumes of non-visible domain imagery by image-to-image (I2I) translation from the visible image domain. Furthermore, we show that the generation of interpolated mixed class (non-visible domain) image examples via our novel Conditional CycleGAN Mixup Augmentation (C2GMA) methodology can lead to a significant improvement in the quality of non-visible domain classification tasks that otherwise suffer due to limited data availability. Focusing on classification within the Synthetic Aperture Radar (SAR) domain, our approach is evaluated on a variation of the Statoil/C-CORE Iceberg Classifier Challenge dataset and achieves 75.4% accuracy, demonstrating a significant improvement when compared against traditional data augmentation strategies (Rotation, Mixup, and MixCycleGAN).

Hiroshi Sasaki, Miguel A. Arroyo, M. Tarek Ibn Ziad et al.

Recent rapid strides in memory safety tools and hardware have improved software quality and security. While coarse-grained memory safety has improved, achieving memory safety at the granularity of individual objects remains a challenge due to high performance overheads which can be between ~1.7x-2.2x. In this paper, we present a novel idea called Califorms, and associated program observations, to obtain a low overhead security solution for practical, byte-granular memory safety. The idea we build on is called memory blacklisting, which prohibits a program from accessing certain memory regions based on program semantics. State of the art hardware-supported memory blacklisting while much faster than software blacklisting creates memory fragmentation (of the order of few bytes) for each use of the blacklisted location. In this paper, we observe that metadata used for blacklisting can be stored in dead spaces in a program's data memory and that this metadata can be integrated into microarchitecture by changing the cache line format. Using these observations, Califorms based system proposed in this paper reduces the performance overheads of memory safety to ~1.02x-1.16x while providing byte-granular protection and maintaining very low hardware overheads. The low overhead offered by Califorms enables always on, memory safety for small and large objects alike, and the fundamental idea of storing metadata in empty spaces, and microarchitecture can be used for other security and performance applications.