Events

In this talk, we discuss the paper “Fast training of accurate physics-informed neural networks without gradient descent” by Chinmay Datar et al., ICLR, 2026. Abstract: Solving time-dependent Partial Differential Equations (PDEs) is one of the most critical problems in computational science. While Physics-Informed Neural Networks (PINNs) offer a promising framework for approximating PDE solutions, their …

In this talk, we discuss the paper "AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML" by Patara Trirat et al, ICML, 2025. Abstract: Automated machine learning (AutoML) accelerates AI development by automating tasks in the development pipeline, such as optimal model search and hyperparameter tuning. Existing AutoML systems often require technical expertise to set up …

In this talk, we discuss the paper "Evolution of error correction through a need for speed" by Riccardo Ravasio et al., Science, 2026. Abstract: Kinetic proofreading is a class of error-correcting mechanisms in biology that expend energy to avoid mistakes during replication, transcription, and translation. Proofreading is typically assumed to evolve when selection for fidelity …

In this talk, we discuss the paper "Dynamical Causality Under Latent Confounders for Biological Network Reconstruction" by Jinling Yang et al, IEEE Transactions on Pattern Analysis and Machine Intelligence (2026). Abstract: Causal interaction inference is prone to spurious causal interactions, due to the substantial confounders in a biological system. While many existing methods attempt to address …

In this talk, we discuss the paper "Towards a General Intelligence and Interface for Wearable Health Data" by Girish Narayanswamy et al., arXiv, 2026. Abstract: While ubiquitous wearable sensors capture a wealth of behavioral and physiological information, effectively transforming these signals into personalized health insights is challenging. Specifically, converting low-level sensor data into representations capable …

In this Journal club, we will discuss the paper "Identification of predictive subphenotypes for clinical outcomes using real world data and machine learning", Weishen Pan et al., Nature Communications, 2025. Abstract: Predicting treatment response is an important problem in real-world applications, where the heterogeneity of the treatment response remains a significant challenge in practice. Unsupervised …

In this talk, we discuss the paper "Learning to learn ecosystems from limited data" by Zheng-Meng Zhai et al., PNAS, 2025. Abstract: A fundamental challenge in developing data-driven approaches to ecological systems for tasks such as state estimation and prediction is the paucity of the observational or measurement data. For example, modern machine-learning techniques such …