arXiv subjects

Rio Yokota

Publications and source records attributed to Rio Yokota.

At least 37 records · Page 2Linked to original sources

arXiv2025

Why We Build Local Large Language Models: An Observational Analysis from 35 Japanese and Multilingual LLMs

Why do we build local large language models (LLMs)? What should a local LLM learn from the target language? Which abilities can be transferred from other languages? Do language-specific scaling laws exist? To explore these research questions, we evaluated 35 Japanese, English, and multilingual LLMs on 19 evaluation benchmarks for Japanese and English, taking Japanese as a local language. Adopting an observational approach, we analyzed correlations of benchmark scores, and conducted principal component analysis (PCA) on the scores to derive \textit{ability factors} of local LLMs. We found that training on English text can improve the scores of academic subjects in Japanese (JMMLU). In addition, it is unnecessary to specifically train on Japanese text to enhance abilities for solving Japanese code generation, arithmetic reasoning, commonsense, and reading comprehension tasks. In contrast, training on Japanese text could improve question-answering tasks about Japanese knowledge and English-Japanese translation, which indicates that abilities for solving these two tasks can be regarded as \textit{Japanese abilities} for LLMs. Furthermore, we confirmed that the Japanese abilities scale with the computational budget for Japanese text.

cs.CL↗

arXiv2025

Building Instruction-Tuning Datasets from Human-Written Instructions with Open-Weight Large Language Models

Instruction tuning is crucial for enabling Large Language Models (LLMs) to solve real-world tasks. Prior work has shown the effectiveness of instruction-tuning data synthesized solely from LLMs, raising a fundamental question: Do we still need human-originated signals for instruction tuning? This work answers the question affirmatively: we build state-of-the-art instruction-tuning datasets sourced from human-written instructions, by simply pairing them with LLM-generated responses. LLMs fine-tuned on our datasets consistently outperform those fine-tuned on existing ones. Our data construction approach can be easily adapted to other languages; we build datasets for Japanese and confirm that LLMs tuned with our data reach state-of-the-art performance. Analyses suggest that instruction-tuning in a new language allows LLMs to follow instructions, while the tuned models exhibit a notable lack of culture-specific knowledge in that language. The datasets and fine-tuned models will be publicly available. Our datasets, synthesized with open-weight LLMs, are openly distributed under permissive licenses, allowing for diverse use cases.

cs.CL↗

arXiv2025

Lion Cub: Minimizing Communication Overhead in Distributed Lion

Communication overhead is a key challenge in distributed deep learning, especially on slower Ethernet interconnects, and given current hardware trends, communication is likely to become a major bottleneck. While gradient compression techniques have been explored for SGD and Adam, the Lion optimizer has the distinct advantage that its update vectors are the output of a sign operation, enabling straightforward quantization. However, simply compressing updates for communication and using techniques like majority voting fails to lead to end-to-end speedups due to inefficient communication algorithms and reduced convergence. We analyze three factors critical to distributed learning with Lion: optimizing communication methods, identifying effective quantization methods, and assessing the necessity of momentum synchronization. Our findings show that quantization techniques adapted to Lion and selective momentum synchronization can significantly reduce communication costs while maintaining convergence. We combine these into Lion Cub, which enables up to 5x speedups in end-to-end training compared to Lion. This highlights Lion's potential as a communication-efficient solution for distributed training.

cs.LG↗

arXiv2025

Masked Gated Linear Unit

Gated Linear Units (GLUs) have become essential components in the feed-forward networks of state-of-the-art Large Language Models (LLMs). However, they require twice as many memory reads compared to feed-forward layers without gating, due to the use of separate weight matrices for the gate and value streams. To address this bottleneck, we introduce Masked Gated Linear Units (MGLUs), a novel family of GLUs with an efficient kernel implementation. The core contribution of MGLUs include: (1) the Mixture of Element-wise Gating (MoEG) architecture that learns multiple binary masks, each determining gate or value assignments at the element level on a single shared weight matrix resulting in reduced memory transfer, and (2) FlashMGLU, a hardware-friendly kernel that yields up to a 19.7 $\times$ inference-time speed-up over a naive PyTorch MGLU and is 47% more memory-efficient and 34% faster than standard GLUs despite added architectural complexity on an RTX5090 GPU. In LLM experiments, the Swish-activated variant SwiMGLU preserves its memory advantages while matching - or even surpassing - the downstream accuracy of the SwiGLU baseline.

cs.LG↗

arXiv2025

Improving LoRA with Variational Learning

Bayesian methods have recently been used to improve LoRA finetuning and, although they improve calibration, their effect on other metrics (such as accuracy) is marginal and can sometimes even be detrimental. Moreover, Bayesian methods also increase computational overheads and require additional tricks for them to work well. Here, we fix these issues by using a recently proposed variational algorithm called IVON. We show that IVON is easy to implement and has similar costs to AdamW, and yet it can also drastically improve many metrics by using a simple posterior pruning technique. We present extensive results on billion-scale LLMs (Llama and Qwen series) going way beyond the scale of existing applications of IVON. For example, we finetune a Llama-3.2-3B model on a set of commonsense reasoning tasks and improve accuracy over AdamW by 1.3% and reduce ECE by 5.4%, outperforming AdamW and other recent Bayesian methods like Laplace-LoRA and BLoB. Overall, our results show that variational learning with IVON can effectively improve LoRA finetuning.

cs.LG↗

arXiv2025

NeurIPS 2023 Competition: Privacy Preserving Federated Learning Document VQA

The Privacy Preserving Federated Learning Document VQA (PFL-DocVQA) competition challenged the community to develop provably private and communication-efficient solutions in a federated setting for a real-life use case: invoice processing. The competition introduced a dataset of real invoice documents, along with associated questions and answers requiring information extraction and reasoning over the document images. Thereby, it brings together researchers and expertise from the document analysis, privacy, and federated learning communities. Participants fine-tuned a pre-trained, state-of-the-art Document Visual Question Answering model provided by the organizers for this new domain, mimicking a typical federated invoice processing setup. The base model is a multi-modal generative language model, and sensitive information could be exposed through either the visual or textual input modality. Participants proposed elegant solutions to reduce communication costs while maintaining a minimum utility threshold in track 1 and to protect all information from each document provider using differential privacy in track 2. The competition served as a new testbed for developing and testing private federated learning methods, simultaneously raising awareness about privacy within the document image analysis and recognition community. Ultimately, the competition analysis provides best practices and recommendations for successfully running privacy-focused federated learning challenges in the future.

cs.LG↗

arXiv2025

Scaling Large-scale GNN Training to Thousands of Processors on CPU-based Supercomputers

Graph Convolutional Networks (GCNs), particularly for large-scale graphs, are crucial across numerous domains. However, training distributed full-batch GCNs on large-scale graphs suffers from inefficient memory access patterns and high communication overhead. To address these challenges, we introduce \method{}, an efficient and scalable distributed GCN training framework tailored for CPU-powered supercomputers. Our contributions are threefold: (1) we develop general and efficient aggregation operators designed for irregular memory access, (2) we propose a hierarchical aggregation scheme that reduces communication costs without altering the graph structure, and (3) we present a communication-aware quantization scheme to enhance performance. Experimental results demonstrate that \method{} achieves a speedup of up to 6$\times$ compared with the SoTA implementations, and scales to 1000s of HPC-grade CPUs on the largest publicly available datasets, without sacrificing model convergence and accuracy. Moreover, due to the effective strong scaling of \method{}, we outperform SoTA GPU-based and CPU-based distributed full-batch GCN training frameworks, in absolute performance, for large-scale graphs.

cs.DC↗

arXiv2025

Local Loss Optimization in the Infinite Width: Stable Parameterization of Predictive Coding Networks and Target Propagation

Local learning, which trains a network through layer-wise local targets and losses, has been studied as an alternative to backpropagation (BP) in neural computation. However, its algorithms often become more complex or require additional hyperparameters because of the locality, making it challenging to identify desirable settings in which the algorithm progresses in a stable manner. To provide theoretical and quantitative insights, we introduce the maximal update parameterization ($μ$P) in the infinite-width limit for two representative designs of local targets: predictive coding (PC) and target propagation (TP). We verified that $μ$P enables hyperparameter transfer across models of different widths. Furthermore, our analysis revealed unique and intriguing properties of $μ$P that are not present in conventional BP. By analyzing deep linear networks, we found that PC's gradients interpolate between first-order and Gauss-Newton-like gradients, depending on the parameterization. We demonstrate that, in specific standard settings, PC in the infinite-width limit behaves more similarly to the first-order gradient. For TP, even with the standard scaling of the last layer, which differs from classical $μ$P, its local loss optimization favors the feature learning regime over the kernel regime.

cs.LG↗

arXiv2025

Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization

The Mixture of Experts (MoE) architecture reduces the training and inference cost significantly compared to a dense model of equivalent capacity. Upcycling is an approach that initializes and trains an MoE model using a pre-trained dense model. While upcycling leads to initial performance gains, the training progresses slower than when trained from scratch, leading to suboptimal performance in the long term. We propose Drop-Upcycling - a method that effectively addresses this problem. Drop-Upcycling combines two seemingly contradictory approaches: utilizing the knowledge of pre-trained dense models while statistically re-initializing some parts of the weights. This approach strategically promotes expert specialization, significantly enhancing the MoE model's efficiency in knowledge acquisition. Extensive large-scale experiments demonstrate that Drop-Upcycling significantly outperforms previous MoE construction methods in the long term, specifically when training on hundreds of billions of tokens or more. As a result, our MoE model with 5.9B active parameters achieves comparable performance to a 13B dense model in the same model family, while requiring approximately 1/4 of the training FLOPs. All experimental resources, including source code, training data, model checkpoints and logs, are publicly available to promote reproducibility and future research on MoE.

cs.CL↗

arXiv2025

On the Relationship Between Double Descent of CNNs and Shape/Texture Bias Under Learning Process

The double descent phenomenon, which deviates from the traditional bias-variance trade-off theory, attracts considerable research attention; however, the mechanism of its occurrence is not fully understood. On the other hand, in the study of convolutional neural networks (CNNs) for image recognition, methods are proposed to quantify the bias on shape features versus texture features in images, determining which features the CNN focuses on more. In this work, we hypothesize that there is a relationship between the shape/texture bias in the learning process of CNNs and epoch-wise double descent, and we conduct verification. As a result, we discover double descent/ascent of shape/texture bias synchronized with double descent of test error under conditions where epoch-wise double descent is observed. Quantitative evaluations confirm this correlation between the test errors and the bias values from the initial decrease to the full increase in test error. Interestingly, double descent/ascent of shape/texture bias is observed in some cases even in conditions without label noise, where double descent is thought not to occur. These experimental results are considered to contribute to the understanding of the mechanisms behind the double descent phenomenon and the learning process of CNNs in image recognition.

cs.CV↗

arXiv2025

An inherently parallel H2-ULV factorization for solving dense linear systems on GPUs

Hierarchical low-rank approximation of dense matrices can reduce the complexity of their factorization from O(N^3) to O(N). However, the complex structure of such hierarchical matrices makes them difficult to parallelize. The block size and ranks can vary between the sub-blocks, which creates load imbalance. The dependency between the sub-blocks during factorization results in serialization. Since many sub-blocks are low-rank, their small computational load exposes the overhead of runtime systems. The combination of these factors makes it challenging to implement these methods on GPUs. In this work, we show that dense matrices can be factorized with linear complexity, while extracting the potential parallelism of GPUs. This is made possible through the H2-ULV factorization, which removes the dependency on trailing sub-matrices.

cs.DC↗

arXiv2024

LLM-jp: A Cross-organizational Project for the Research and Development of Fully Open Japanese LLMs

This paper introduces LLM-jp, a cross-organizational project for the research and development of Japanese large language models (LLMs). LLM-jp aims to develop open-source and strong Japanese LLMs, and as of this writing, more than 1,500 participants from academia and industry are working together for this purpose. This paper presents the background of the establishment of LLM-jp, summaries of its activities, and technical reports on the LLMs developed by LLM-jp. For the latest activities, visit https://llm-jp.nii.ac.jp/en/.

cs.CL↗

arXiv2024

Aurora-M: Open Source Continual Pre-training for Multilingual Language and Code

Pretrained language models are an integral part of AI applications, but their high computational cost for training limits accessibility. Initiatives such as Bloom and StarCoder aim to democratize access to pretrained models for collaborative community development. Despite these efforts, such models encounter challenges such as limited multilingual capabilities, risks of catastrophic forgetting during continual pretraining, and the high costs of training models from scratch, alongside the need to align with AI safety standards and regulatory frameworks. This paper presents Aurora-M, a 15B parameter multilingual open-source model trained on English, Finnish, Hindi, Japanese, Vietnamese, and code. Continually pretrained from StarCoderPlus on 435B additional tokens, Aurora-M surpasses 2T tokens in total training token count. It is the first open-source multilingual model fine-tuned on human-reviewed safety instructions, thus aligning its development not only with conventional red-teaming considerations, but also with the specific concerns articulated in the Biden-Harris Executive Order on the Safe, Secure, and Trustworthy Development and Use of Artificial Intelligence. We evaluate Aurora-M across a wide range of tasks and languages, showcasing its robustness against catastrophic forgetting and its superior performance in multilingual settings, particularly in safety evaluations. We open-source Aurora-M and its variants to encourage responsible open-source development of large language models at https://huggingface.co/aurora-m.

cs.CL↗

arXiv2024

Accelerating Large Language Model Training with 4D Parallelism and Memory Consumption Estimator

In large language model (LLM) training, several parallelization strategies, including Tensor Parallelism (TP), Pipeline Parallelism (PP), Data Parallelism (DP), as well as Sequence Parallelism (SP) and Context Parallelism (CP), are employed to distribute model parameters, activations, and optimizer states across devices. Identifying the optimal parallelization configuration for each environment while avoiding GPU memory overflow remains a challenging task. In this study, we provide precise formulas to estimate the memory consumed by parameters, gradients, optimizer states, and activations for 4D parallel training (DP, TP, PP, CP) in the Llama architecture. We conducted 454 experiments on A100 and H100 GPUs, incorporating often neglected factors such as temporary buffers and memory fragmentation into our analysis. Results indicate that when the estimated memory usage is below 80\% of the available GPU memory, the training never encounters out-of-memory errors. This simple yet effective formula allows us to identify parallelization configurations that could lead to memory overflow in advance, significantly reducing the configuration search space. Additionally, through a comprehensive exploration of optimal configurations in 4D parallelism, our analysis of the 454 experimental results provides empirical insights into optimal 4D parallelism configurations.

cs.LG↗

arXiv2024

Balancing Speed and Stability: The Trade-offs of FP8 vs. BF16 Training in LLMs

Large Language Models (LLMs) have attracted significant attention due to their human-like language understanding and generation capabilities, as well as their applicability across various domains. These models, characterized by their massive scale and extensive training data, continue to push the boundaries of what is possible in natural language processing. The Llama 3 series, for instance, exemplifies this trend with its flagship model boasting 405 billion parameters trained on 15.6 trillion tokens. The immense computational demands associated with training such models have spurred ongoing research into optimizing the efficiency of the training process, particularly through the use of lower-precision formats. NVIDIA's H100 GPU, which introduces support for FP8 in addition to the more conventional FP16 and BF16 formats, has emerged as a focal point in this optimization effort. Preliminary studies suggest that FP8 could offer substantial reductions in training time without sacrificing model performance when compared to BF16, making it a promising candidate for large-scale model training. However, the broader implications of adopting FP8, particularly in terms of training stability and downstream task performance, have yet to be fully understood. In this study, we delve into the practical trade-offs involved in adopting FP8 over BF16 for training LLMs.

cs.LG↗

arXiv2024

Variational Low-Rank Adaptation Using IVON

We show that variational learning can significantly improve the accuracy and calibration of Low-Rank Adaptation (LoRA) without a substantial increase in the cost. We replace AdamW by the Improved Variational Online Newton (IVON) algorithm to finetune large language models. For Llama-2 with 7 billion parameters, IVON improves the accuracy over AdamW by 2.8% and expected calibration error by 4.6%. The accuracy is also better than the other Bayesian alternatives, yet the cost is lower and the implementation is easier. Our work provides additional evidence for the effectiveness of IVON for large language models. The code is available at https://github.com/team-approx-bayes/ivon-lora.

cs.LG↗

arXiv2024

Formula-Supervised Visual-Geometric Pre-training

Throughout the history of computer vision, while research has explored the integration of images (visual) and point clouds (geometric), many advancements in image and 3D object recognition have tended to process these modalities separately. We aim to bridge this divide by integrating images and point clouds on a unified transformer model. This approach integrates the modality-specific properties of images and point clouds and achieves fundamental downstream tasks in image and 3D object recognition on a unified transformer model by learning visual-geometric representations. In this work, we introduce Formula-Supervised Visual-Geometric Pre-training (FSVGP), a novel synthetic pre-training method that automatically generates aligned synthetic images and point clouds from mathematical formulas. Through cross-modality supervision, we enable supervised pre-training between visual and geometric modalities. FSVGP also reduces reliance on real data collection, cross-modality alignment, and human annotation. Our experimental results show that FSVGP pre-trains more effectively than VisualAtom and PC-FractalDB across six tasks: image and 3D object classification, detection, and segmentation. These achievements demonstrate FSVGP's superior generalization in image and 3D object recognition and underscore the potential of synthetic pre-training in visual-geometric representation learning. Our project website is available at https://ryosuke-yamada.github.io/fdsl-fsvgp/.

cs.CV↗

arXiv2024

Rethinking Image Super-Resolution from Training Data Perspectives

In this work, we investigate the understudied effect of the training data used for image super-resolution (SR). Most commonly, novel SR methods are developed and benchmarked on common training datasets such as DIV2K and DF2K. However, we investigate and rethink the training data from the perspectives of diversity and quality, {thereby addressing the question of ``How important is SR training for SR models?''}. To this end, we propose an automated image evaluation pipeline. With this, we stratify existing high-resolution image datasets and larger-scale image datasets such as ImageNet and PASS to compare their performances. We find that datasets with (i) low compression artifacts, (ii) high within-image diversity as judged by the number of different objects, and (iii) a large number of images from ImageNet or PASS all positively affect SR performance. We hope that the proposed simple-yet-effective dataset curation pipeline will inform the construction of SR datasets in the future and yield overall better models.

cs.CV↗