450 citations · 593 across the 25 of their papers we have counts for
26 papers
MLIP Detective: Active Failure Mode Discovery Beyond Benchmark Scores for Machine-Learning Interatomic Potentials
Ryuhei Okuno, Nontawat Charoenphakdee, Kaoru Hisama +1
Universal machine-learning interatomic potentials (u-MLIPs) aim to generalize across diverse configurations. Benchmarks enable reproducible evaluation but may not expose failures o…
Do Coding Agents Deceive Us? Detecting and Preventing Cheating via Capped Evaluation with Randomized Tests
Thanawat Lodkaew, Johannes Ackermann, Soichiro Nishimori +3
A growing failure mode in agent evaluation and training is that models can achieve high evaluation scores by exploiting shortcuts instead of solving the intended task, producing de…
Lang2MLIP: End-to-End Language-to-Machine Learning Interatomic Potential Development with Autonomous Agentic Workflows
Wenwen Li, Yuki Orimo, Nontawat Charoenphakdee
Developing machine learning interatomic potentials (MLIPs) for complex materials systems remains challenging because it requires expertise in atomistic simulations, machine learnin…
LightPFP: A Lightweight Route to Ab Initio Accuracy at Scale
Wenwen Li, Nontawat Charoenphakdee, Yong-Bin Zhuang +5
Atomistic simulation methods have evolved through successive computational levels, each building upon more fundamental approaches: from quantum mechanics to density functional theo…
P-DRUM: Post-hoc Descriptor-based Residual Uncertainty Modeling for Machine Learning Potentials
Shih-Peng Huang, Nontawat Charoenphakdee, Yuta Tsuboi +2
Ensemble method is considered the gold standard for uncertainty quantification (UQ) in machine learning interatomic potentials (MLIPs). However, their high computational cost can l…
Virtual Human Generative Model: Masked Modeling Approach for Learning Human Characteristics
Kenta Oono, Nontawat Charoenphakdee, Kotatsu Bito +14
Virtual Human Generative Model (VHGM) is a generative model that approximates the joint probability over more than 2000 human healthcare-related attributes. This paper presents the…
Diffusion models for missing value imputation in tabular data
Shuhan Zheng, Nontawat Charoenphakdee
Missing value imputation in machine learning is the task of estimating the missing values in the dataset accurately using available information. In this task, several deep generati…
Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary Classification
Takashi Ishida, Ikko Yamane, Nontawat Charoenphakdee +2
There is a fundamental limitation in the prediction performance that a machine learning model can achieve due to the inevitable uncertainty of the prediction target. In classificat…
Cross-lingual Transfer for Text Classification with Dictionary-based Heterogeneous Graph
Nuttapong Chairatanakul, Noppayut Sriwatanasakdi, Nontawat Charoenphakdee +2
In cross-lingual text classification, it is required that task-specific training data in high-resource source languages are available, where the task is identical to that of a low-…
Towards Universal Neural Network Potential for Material Discovery Applicable to Arbitrary Combination of 45 Elements
So Takamoto, Chikashi Shinagawa, Daisuke Motoki +19
Computational material discovery is under intense study owing to its ability to explore the vast space of chemical systems. Neural network potentials (NNPs) have been shown to be p…
A Symmetric Loss Perspective of Reliable Machine Learning
Nontawat Charoenphakdee, Jongyeong Lee, Masashi Sugiyama
When minimizing the empirical risk in binary classification, it is a common practice to replace the zero-one loss with a surrogate loss to make the learning objective feasible to o…
On Focal Loss for Class-Posterior Probability Estimation: A Theoretical Perspective
Nontawat Charoenphakdee, Jayakorn Vongkulbhisal, Nuttapong Chairatanakul +1
The focal loss has demonstrated its effectiveness in many real-world applications such as object detection and image classification, but its theoretical understanding has been limi…
Classification with Rejection Based on Cost-sensitive Classification
Nontawat Charoenphakdee, Zhenghang Cui, Yivan Zhang +1
The goal of classification with rejection is to avoid risky misclassification in error-critical applications such as medical diagnosis and product inspection. In this paper, based…
Robust Imitation Learning from Noisy Demonstrations
Voot Tangkaratt, Nontawat Charoenphakdee, Masashi Sugiyama
Robust learning from noisy demonstrations is a practical but highly challenging problem in imitation learning. In this paper, we first theoretically show that robust imitation lear…
Learning from Aggregate Observations
Yivan Zhang, Nontawat Charoenphakdee, Zhenguo Wu +1
We study the problem of learning from aggregate observations where supervision signals are given to sets of instances instead of individual instances, while the goal is still to pr…
Time-varying Gaussian Process Bandit Optimization with Non-constant Evaluation Time
Hideaki Imamura, Nontawat Charoenphakdee, Futoshi Futami +3
The Gaussian process bandit is a problem in which we want to find a maximizer of a black-box function with the minimum number of function evaluations. If the black-box function var…
Learning Only from Relevant Keywords and Unlabeled Documents
Nontawat Charoenphakdee, Jongyeong Lee, Yiping Jin +2
We consider a document classification problem where document labels are absent but only relevant keywords of a target class and unlabeled documents are given. Although heuristic me…
Learning from Indirect Observations
Yivan Zhang, Nontawat Charoenphakdee, Masashi Sugiyama
Weakly-supervised learning is a paradigm for alleviating the scarcity of labeled data by leveraging lower-quality but larger-scale supervision signals. While existing work mainly f…
Classification from Triplet Comparison Data
Zhenghang Cui, Nontawat Charoenphakdee, Issei Sato +1
Learning from triplet comparison data has been extensively studied in the context of metric learning, where we want to learn a distance metric between two instances, and ordinal em…
Imitation Learning from Imperfect Demonstration
Yueh-Hua Wu, Nontawat Charoenphakdee, Han Bao +2
Imitation learning (IL) aims to learn an optimal policy from demonstrations. However, such demonstrations are often imperfect since collecting optimal ones is costly. To effectivel…
Semi-Supervised Ordinal Regression Based on Empirical Risk Minimization
Taira Tsuchiya, Nontawat Charoenphakdee, Issei Sato +1
Ordinal regression is aimed at predicting an ordinal class label. In this paper, we consider its semi-supervised formulation, in which we have unlabeled data along with ordinal-lab…
On the Calibration of Multiclass Classification with Rejection
Chenri Ni, Nontawat Charoenphakdee, Junya Honda +1
We investigate the problem of multiclass classification with rejection, where a classifier can choose not to make a prediction to avoid critical misclassification. First, we consid…
Domain Discrepancy Measure for Complex Models in Unsupervised Domain Adaptation
Jongyeong Lee, Nontawat Charoenphakdee, Seiichi Kuroki +1
Appropriately evaluating the discrepancy between domains is essential for the success of unsupervised domain adaptation. In this paper, we first point out that existing discrepancy…
On Symmetric Losses for Learning from Corrupted Labels
Nontawat Charoenphakdee, Jongyeong Lee, Masashi Sugiyama
This paper aims to provide a better understanding of a symmetric loss. First, we emphasize that using a symmetric loss is advantageous in the balanced error rate (BER) minimization…