← Search

Atsuhiro Takasu

5 accepted papers

2026

Format Matters: The Robustness of Multimodal LLMs in Reviewing Evidence from Tables and Charts

AAAI 2026technical

With the growing number of submitted scientific papers, there is an increasing demand for systems that can assist reviewers in evaluating research claims. Experimental results are a core component of scientific work, often presented in varying formats such as tables or charts. Understanding how robu

Cited by 0SourcePDFScholar
2025

Table-Text Alignment: Explaining Claim Verification Against Tables in Scientific Papers

EMNLP 2025

Scientific claim verification against tables typically requires predicting whether a claim is supported or refuted given a table. However, we argue that predicting the final label alone is insufficient: it reveals little about the model’s reasoning and offers limited interpretability. To address thi

2022

MEIM: Multi-partition Embedding Interaction Beyond Block Term Format for Efficient and Expressive Link Prediction

IJCAI 2022poster

Knowledge graph embedding aims to predict the missing relations between entities in knowledge graphs. Tensor-decomposition-based models, such as ComplEx, provide a good trade-off between efficiency and expressiveness, that is crucial because of the large size of real world knowledge graphs. The rece…

2021

Fully-Neural Approach to Vehicle Weighing and Strain Prediction on Bridges Using Wireless Accelerometers

ICASSP 2021accepted

Bridge weigh-in-motion (BWIM) is a technique of estimating vehicle loads on bridges and can be used to assess a bridge’s structural fatigue and therefore its life. BWIM can be realized by analyzing the bridge deflection in terms of its response to moving axle loads. To obtain accurate load estimates…

Cited by 0SourceScholar
2020

Fully-Neural Approach to Heavy Vehicle Detection on Bridges Using a Single Strain Sensor

ICASSP 2020accepted

Bridge weigh-in-motion (BWIM) is a technique for detecting heavy vehicles that may cause serious damage to real bridges. BWIM is realized by analyzing the strain signals observed at places on the bridge in terms of bridge-component responses to the axle loads. In current practice, a BWIM system requ…

Cited by 0SourceScholar