HeyJaredCRUNCH Group: Home of Math + Machine Learning + X
This channel puts all the seminars that are weekly held at the CRUNCH Group, Division of Applied Mathematics, Brown University, USA. This group is the home of PINNs, DeepONet and much more!!!
- Indexed videos, last 90 days
- 11
- Latest publication
- Sep 25, 2026
- Audience
- ~4K subscribers
- Earliest in this view
- Jul 12, 2026
Latest videos
Component-Access Subspace Optimization || Sep 25, 2026 (opens the original)
Read excerpt
Speakers, institutes & title 1) Meet Dabgar, NIT Surat & Aaditya L. Kachhadiya, independent researcher, Component-Access Subspace Optimization: Rethinking Directional Representability in Scalarized Scientific Learning Abstract: Many learning problems in physics-informed and scientific machine learning minimize scalarized objectives built from heterogeneous components — PDE residuals, boundary and initial conditions, and task-specific losses. Existing approaches address imbalance between these co
Generative in-Context Operator Learning for UQ|| Neuroscience Inspired DL Algorithms|| Aug 21, 2026 (opens the original)
Read excerpt
Speakers, institutes & titles 1) Benjamin Zhang, UNC Chapel Hill, Generative in-Context Operator Learning for Uncertainty Quantification in Foundation Models of Differential Equations Abstract: In-context operator networks (ICON) are a class of operator learning methods based on the novel architectures of foundation models. Trained on a diverse set of datasets of initial and boundary conditions paired with corresponding solutions to ordinary and partial differential equations (ODEs and PDEs), IC
An Optimization Framework for the Well-Conditioned Training of PINNs || Sep 11, 2026 (opens the original)
Read excerpt
Speaker, institute & title 1) Joseph Webb, University of Oxford, An Optimisation Framework for the Well-Conditioned Training of PINNs Abstract: Physics-informed neural networks (PINNs) have emerged as a promising route to solve partial differential equations, yet they have struggled to reach the precision of classical solvers. The obstacle is increasingly understood to be one of optimisation, owing to the severely ill-conditioned loss landscape. We present a scalable second-order optimisation fr
From Shadowgraphs to Topology || Sep 4, 2026 (opens the original)
Read excerpt
Speaker, institute & title 1) Yash Bisht, Indian Institute of Technology Roorkee, Topology-Aware Morphology States for Near-Nozzle Air-Assisted. Atomization: From Experimental Imaging to Scientific Machine Learning Abstract: Near-nozzle air-assisted atomization contains a connected liquid core,perforations, ligaments and detached fragments within the same optically dense projection, making conventional droplet-level descriptions incomplete. This talk presents a topology-aware framework that trea
Physics informed neural networks with applications to environmental hydraulics || Aug 28, 2026 (opens the original)
Read excerpt
Speaker, institute & title 1) Prof. Qingzhi Hou, Tianjin University, Improved physics informed neural networks with applications to environmental hydraulics Abstract: Physics-informed Neural Networks (PINNs) have emerged as a highly promising paradigm at the intersection of scientific computing and artificial intelligence, specifically tailored for solving complex Partial Differential Equations (PDEs). The core philosophy involves embedding governing physical equations directly as prior constrai
Publishing over time
Last 90 days. Choose a month to open its work.
Recurring subjects
Named in the text we hold. One piece can cover several.
Audience
~4K subscribers
Measured Sep 19, 2026
Source's subscribers, not the number who saw an individual piece.
About this data
Counts cover the work we have indexed. Tone needs enough text and a confident classification. Excerpts and episode notes are not full articles or transcripts.
Identity or attribution wrong? Suggest a correction.
See coverage about CRUNCH Group: Home of Math + Machine Learning + X