8 papers
Intervention-Based Time Series Causal Discovery via Simulator-Generated Interventional Distributions
Tsuyoshi Okita
We propose SVAR-FM (Structural VAR with Flow Matching), a framework for time series causal discovery that treats a physics-based simulator as a mechanical realization of Pearl's do…
Mathematical Reasoning via Intervention-Based Time-Series Causal Discovery Using LLMs as Concept Mastery Simulators
Tsuyoshi Okita
Recent methods for improving LLM mathematical reasoning, whether through MCTS-based test-time search or causal graph-guided knowledge injection, cannot identify which concepts caus…
Excluding the Target Domain Improves Extrapolation: Deconfounded Hierarchical Physics Constraints
Tsuyoshi Okita
Extrapolation to out-of-distribution conditions is a fundamental challenge for physics-constrained deep generative models. Existing methods apply physical constraints as a single s…
Physical Simulators as Do-Operators: Causal Discovery under Latent Confounders for AI-for-Science
Tsuyoshi Okita
Existing interventional causal discovery methods -- IGSP, DCDI, ENCO -- assume causal sufficiency (no latent confounders) and rely on virtual interventions in synthetic simulators.…
Bridging the Physics-Data Gap with FNO-Guided Conditional Flow Matching: Designing Inductive Bias through Hierarchical Physical Constraints
Tsuyoshi Okita
Conventional time-series generation often ignores domain-specific physical constraints, limiting statistical and physical consistency. We propose a hierarchical framework that embe…
Knowledge Distillation for Reservoir-based Classifier: Human Activity Recognition
Masaharu Kagiyama, Tsuyoshi Okita
This paper aims to develop an energy-efficient classifier for time-series data by introducing PatchEchoClassifier, a novel model that leverages a reservoir-based mechanism known as…
Self-supervised Learning Method Using Transformer for Multi-dimensional Sensor Data Processing
Haruki Kai, Tsuyoshi Okita
We developed a deep learning algorithm for human activity recognition using sensor signals as input. In this study, we built a pretrained language model based on the Transformer ar…
Brain Hematoma Marker Recognition Using Multitask Learning: SwinTransformer and Swin-Unet
Kodai Hirata, Tsuyoshi Okita
This paper proposes a method MTL-Swin-Unet which is multi-task learning using transformers for classification and semantic segmentation. For spurious-correlation problems, this met…