Some of our presenters couldn’t attend the workshop in person. They kindly sent us a video or poster presentation of their work. Please find them listed with Video Link or Poster Link in front of the corresponding paper below.

Oral Presentations

• Vendi Information Gain for Active Learning and its Application to Ecology

• Batch Acquisition Function Evaluations and Decouple Optimizer Updates for Faster Bayesian Optimization

• FG-ConvNO: A Geometry-Aware Neural Operator for Propeller CFD Prediction

• MNO: A Multi-modal Neural Operator for Parametric Nonlinear BVPs Video Link

Poster Presentations

• Towards Fine-Tuning-Based Site Calibration for Knowledge-Guided Machine Learning

• CORONA-FIELDS: Leveraging Foundation Models for Classification of Solar Wind Phenomena

• Interpretable, Redshift-Free Photometric Typing of Type~Ia Supernovae for the Rubin LSST

• Hyperspectral Variational Autoencoders for Joint Data Compression and Component Extraction

• DECOR: Deep Embedding Clustering with Orientation Robustness Poster Link

• Dual-Head Physics-Informed Graph Decision Transformer for Distribution System Restoration

• The Promise of Reinforcement Learning for Controlling Ion Micromotion in RF Paul Traps

• Physics-Informed Symbolic Regression Discovers Simple Analytic Approximations for the Steady Swift–Hohenberg Equation in Polar Coordinates

• Towards a Foundation Model for Partial Differential Equations Across Physics Domains

• Prometheus: Unsupervised Discovery of Phase Transitions Through Physics-Informed Variational Autoencoders

• Meta-Learning for Physics-Informed Neural Networks: A Framework for Few-Shot Adaptation in Parametric PDEs

• TLE-Based A2C Agent for Terrestrial Coverage Orbital Path Planning

• Accelerating Machine Learning Force Field Inference with Atom Type Specific Scheduling

• SCOPES: Stability-Aware Cross-Platform Feature Selection for Matched TCGA Gene Expression and RNA-Seq Data

• Resilient AI Infrastructure by Design: A Spatially-Aware Framework for Tolerating Clustered Failures

• Five Years of SciCap: What We Learned and Future Directions for Scientific Figure Captioning

• CloudNFMM: A Hybrid Hierarchical and Local Neural Operator Inspired by the Fast Multipole Method

• A General Pipeline for LLM Finetune Ingestion of Scientific Tabular Data

• Symmetry-Aware Contrastive Learning for Self-Supervised Crop Intelligence from Satellite and Ecological Data

• Physics-Guided Diffusion Priors for Multi-Slice Reconstruction in Scientific Imaging

• Generation of Low-Discrepancy Point Sets and Sequences via LLM Evolutionary Search

• Bridging Symbolic and Neural Reasoning: Ontology-Integrated LLMs for Domain-Grounded QA

• MedRule-KG: A Knowledge-Graph–Steered Scaffold for Reliable Mathematical and Biomedical Reasoning

• Using Multi-Modal Diffusion Models to Reconstruct Dark Matter Fields

• When Less is More: A Story of Failing Bayesian Optimization Due to Additional Expert Knowledge

• Sumudu Neural Operator for ODEs and PDEs

• Self-Supervised Affordance Reinforcement Learning Framework for Robotic Grasping