Institution profile

RIKEN

Academic institutionasia · jp
Official website
Research library472linked papers
Opportunities0open roles
Selected work

Representative Papers

Accurate Forgetting for Heterogeneous Federated Continual Learning

Feb 20, 2025International Conference on Learning Representations

To address statistical bias and noise interference arising from client data/task heterogeneity—or even adversarial behavior—in federated continual learning (FCL), this paper introduces the “Accurate Forgetting” (AF) paradigm: proactively identifying and discarding unreliable feature representations induced by skewed distributions and noise prior to knowledge reuse. Methodologically, we propose the first probability-based credibility assessment framework built upon normalized flows, enabling quantifiable, knowledge-granular filtering. Further, we integrate generative replay with selective knowledge inheritance to dynamically enhance global model robustness within the federated architecture. Evaluated on multiple heterogeneous FCL benchmarks, AF achieves an average accuracy improvement of 12.3%, significantly boosting generalization and noise resilience. Our approach provides a novel, interpretable, and computationally tractable pathway for bias mitigation in FCL.

5 citationsRead paper

Towards Million-Server Network Simulations on Just a Laptop

May 26, 2021arXiv.org

To address the challenges of assessing non-shortest-path diversity in large-scale interconnection networks and the poor scalability of conventional packet-level simulators, this paper proposes a lightweight simulation framework tailored for extreme-scale networks. By identifying memory and event-scheduling bottlenecks in mainstream simulators, we introduce three core techniques: compact data structures, lazily bound event queues, and lock-free memory pools—significantly reducing both memory footprint and synchronization overhead. Our framework enables fine-grained, packet-level simulation of data center and HPC networks with over one million endpoints on a single commodity laptop, achieving a throughput of 10 million packets per second—three orders of magnitude higher than state-of-the-art shared-memory simulators. The open-source framework supports rapid prototyping and validation of novel interconnect protocols, providing a reproducible, high-fidelity foundation for path diversity analysis and performance optimization in ultra-large-scale networks.

3 citationsRead paper

ASMR: Augmenting Life Scenario using Large Generative Models for Robotic Action Reflection

Jun 16, 2025

To address inaccurate multimodal user intent understanding by domestic service robots under few-shot conditions, this paper proposes a semantics-controllable dialogue–scene image co-generation framework for data augmentation. To overcome the bottlenecks of scarce real-world multimodal data and high annotation costs, our method integrates large language models (LLMs) for contextualized dialogue modeling and reasoning, and leverages Stable Diffusion to synthesize high-fidelity, semantically aligned environment images. This establishes an end-to-end synthetic data generation and fine-tuning pipeline. To the best of our knowledge, this is the first framework enabling joint, controllable generation of linguistic intent and visual context. Experimental results demonstrate substantial improvements in action selection accuracy on real-world benchmark datasets, achieving state-of-the-art (SOTA) performance. The results validate that synthetically generated multimodal data effectively enhances downstream models’ generalization capability across modalities.

2 citationsRead paper

Quantifying Statistical Significance in Diffusion-Based Anomaly Localization via Selective Inference

Feb 19, 2024

Image anomaly localization is critical in medical diagnosis and industrial inspection, yet existing generative-model-based approaches—particularly diffusion models—lack statistical reliability, suffer from model bias and uncertainty, and fail to quantify false-positive risk. This paper introduces selective inference to diffusion-based anomaly localization for the first time, establishing an interpretable statistical inference framework: for each pixel or region in the model-reconstructed image, it performs conditional hypothesis testing and outputs rigorously calibrated p-values to quantify the false-positive probability. Unlike conventional methods lacking theoretical guarantees, our approach enables statistically controlled, significance-aware anomaly localization. Experiments on multiple medical and industrial datasets demonstrate substantial improvements in false-positive rate control, delivering trustworthy, statistically grounded anomaly localization outputs suitable for high-stakes applications.

2 citationsRead paper

Rethinking quantum smooth entropies: Tight one-shot analysis of quantum privacy amplification

Mar 04, 2026

This work investigates the security bounds of randomness extraction against quantum side information in the single-shot setting, i.e., quantum privacy amplification. By introducing a novel quantum smooth conditional entropy derived from a measurement-based classical smooth divergence and proposing a variational formulation of smooth Rényi relative entropy that incorporates smoothing over non-positive Hermitian operators, the authors establish tighter leftover hash lemmas and decoupling bounds. This approach yields, for the first time, an optimal second-order asymptotic expansion valid for all hash functions, significantly improving upon existing smooth min-entropy bounds. The method simultaneously achieves the tightest known single-shot achievability and converse optimality guarantees under trace distance, while also recovering the optimal achievability result in the classical setting.

1 citationsRead paper
Recent publications

Latest Papers