As a fan of traditional machine learning research, I’ll just register here my sadness and discontent that things are going this way. Time was that an effort like this would follow stringent ethical rules for research involving humans that would never ever allow this kind of phony consent theater, would go through a review board •with actual teeth•, would not involve offloading raw personal data to commercial vendors who have the power to slurp it up and repurpose it, would result in a narrowly purposed-tuned model answering to the ethical parameters of the study, would not leave the barn doors wide open to endless open-ended use of personal data…I could go on.
Human-machine learning boosts noninvasive brain-computer control in untrained users https://techxplore.com/news/2026-07-human-machine-boosts-noninvasive-brain.html "working on noninvasive brain-computer interfaces (BCIs) to develop technology that is…
This is so cool! 'Supporting Human and Machine Co-Learning in Citizen Science: Lessons From Gravity Spy' https://theoryandpractice.citizenscienceassociation.org/articles/10.5334/cstp.738
The dream of scaffolding learning has bee…
Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[7/11]:
- Evaluating Universal Machine Learning Force Fields Against Experimental Measurements
Mannan, Bihani, Gonzales, Lee, Gosvami, Ranu, Miret, Krishnan
Long-horizon prediction of three-dimensional wall-bounded turbulence with CTA-Swin-UNet and resolvent analysis
Bo Chen, Yitong Fan, Jie Yao, Weipeng Li
https://arxiv.org/abs/2605.17888 https://arxiv.org/pdf/2605.17888 https://arxiv.org/html/2605.17888
arXiv:2605.17888v1 Announce Type: new
Abstract: Long-horizon prediction of three-dimensional (3D) wall-bounded turbulence with machine-learning methods remains a challenging task, due to the rapid accumulation of autoregressive errors and the substantially computational cost. To address these challenges, we present a hybrid machine-learning framework, in which a channel-time-attention Swin-UNet (CTA-Swin-UNet) and a multi-time-scale fusion correction (MTFC) strategy are developed to predict the turbulent flow fields in a wall-parallel plane, with affordable computational cost. Then, 3D flow fields are reconstructed via a resolvent-based spectral linear stochastic estimation (SLSE), rooting from the predicted planar flow. Results show that the CTA-Swin-UNet outperforms the baseline models (LSTM, FNO and traditional Swin-UNet) in both single-step prediction and autoregressive rollouts, indicating the effectiveness of introducing the CTA module into the Swin-UNet architecture. At the same temporal interval, the CTA-Swin-UNet remains stable for approximately 150 rollout steps, while the baseline models fail within 20 to 50 rollout steps. After introducing the MTFC strategy, a longer horizon upto 300 steps is achieved. Using the resolvent-based SLSE reconstruction further recovers the 3D flow structures and energy spectral distributions from the predicted planar inputs, which demonstrates that the proposed framework provides an effective and computationally efficient approach for long-horizon autoregressive prediction of 3D wall-bounded turbulence.
toXiv_bot_toot
O algoritmo de machine learning do youtube é verdadeiramente genial.
"mix música brasileira" (nunca clico em mixes, mas aparecem-me sempre Š frente, com o raio que os parta): a imagem é o Carlão. Os nomes visíveis são: António Zambujo, Caetano Veloso (vš lš), Os Quatro e Meia.
Genial mesmo!
*Chef's kiss*.
This month on All Space Considered, Griffith Observatory welcomed Dr. Joel Leja, Associate Professor of astronomy & astrophysics at The Pennsylvania State University, to discuss his research on the processes of galaxy formation derived from a combination of statistics, machine learning, and deep galaxy surveys with telescopes like the James Webb Space Telescope: #LittleRedDots
UW CALMA Round Table: AI & ML in Metadata: Possibilities, Limitations, and Ethical Implications (Free online event)
Friday, May 22, 2026, 10:00-11:30 PDT
Morag Boyd, OCLC
Charlene Chou, NYU Libraries
Jeremy Nelson, Stanford University Libraries
Philippe Saadé, Wikimedia Deutschland
Osma Suominen, expert
Denny Vrandečić, Wikimedia Foundation & King’s College London
Crystal Yragui (moderator), UW Libraries
AWS SVP Dave Brown is leaving after 19 years for a new job; he led compute and machine learning services and is a member of the S-team advising Andy Jassy (Greg Bensinger/Reuters)
https://www.reuters.com/technology/amazon-aws-ex…
Predicting when clouds will suddenly dim solar panels has been a major challenge for grid operators. Now an AI model trained in Oklahoma is proving it can forecast these critical "ramp" events at sites worldwide.
Tested at 15 global locations, the model successfully predicts rapid solar power swings by analyzing cloud types and coverage—key for keeping the grid stable as renewables grow.
There’s a classic thought experiment about quality vs efficiency for machine learning in medical diagnosis. I can’t remember where I first heard it, but @… laid it out in a blog post:
https://pluralistic.net/2025/03/18/asbestos-in-the-walls/
2/
Prediction of solar energetic events impacting space weather conditions: #SpaceWeather Challenges: https://eos.org/science-updates/vast-space-sparse-data-an-ai-answer-to-twin-space-weather-challenges - modern machine learning and AI methods can help heliophysics researchers and space weather forecasters overcome limitations from a dearth of observations and the infrequency of extreme events.
The sheer amount of intentionality and thought that went into designing @…'s local ML processing is so heartwarming. It represents the best of what CS can be --- thoughtfully designing software to empower people ♥️
https://ente.com/…
A Scoping Review of Physics Informed Machine Learning for Wave Propagation Modeling in Seismology
\'Oscar Rinc\'on-Carde\~no, Gregorio P\'erez-Bernal, Silvana Montoya-Noguera, Nicol\'as Guar\'in-Zapata
https://arxiv.org/abs/2607.00178 https://arxiv.org/pdf/2607.00178 https://arxiv.org/html/2607.00178
arXiv:2607.00178v1 Announce Type: new
Abstract: \emph{Background:} Standard numerical methods accurately simulate seismic waves but are computationally expensive, particularly for inverse problems. Machine learning approaches have been proposed as alternatives that can reduce computational cost while maintaining acceptable physical accuracy. \emph{Objective:} To map how physics-informed machine learning methods have been applied to seismic wave propagation modeling based on partial differential equations. \emph{Methods:} A scoping review was conducted using the OpenAlex and Scopus databases. Selected studies were classified by problem type (forward or inverse) and machine learning strategy to identify research trends, methodological patterns, and gaps in the literature. \emph{Results:} Physics-informed machine learning has been applied to both forward modeling and inversion in seismology, often reaching accuracy comparable to standard numerical methods at lower computational cost. Application of three mechanisms for incorporating physical knowledge were identified: observational bias, inductive bias, and learning bias. To evaluate methodological reproducibility of a representative method, the original PINN framework was replicated in PyTorch, obtaining results consistent with and in most cases more accurate than those originally reported. From the reviewed literature, limitations remain in benchmarking consistency, training cost, and scalability to three-dimensional and experimentally validated problems. \emph{Conclusions:} Standard numerical methods remain the basis of seismological workflows, while physics-informed machine learning offers complementary approaches that are useful for inverse problems and surrogate modeling. Future work should focus on consistent benchmarking, hybrid formulations, and validation under realistic geophysical conditions.
toXiv_bot_toot
Quantum Occam Learning: Sample-Supported Expressibility for Circuit-Based Quantum Learning
Jeongho Bang, Kyoungho Cho, Jeongwoo Jae
https://arxiv.org/abs/2606.12211 https://arxiv.org/pdf/2606.12211 https://arxiv.org/html/2606.12211
arXiv:2606.12211v1 Announce Type: new
Abstract: A central principle in quantum machine learning is that an ansatz should be expressive enough to represent the quantum data of interest. Yet, the expressibility is statistically meaningful only insofar as it can be learned from finitely many copies of an unknown quantum state. In this work, we develop an information-theoretic Occam theory for quantum data generated by finite-size quantum circuits. For the class $S_{n,G}$ of $n$-qubit pure states preparable with at most $G$ two-qubit gates, a metric-entropy argument gives the realizable sample law $\widetilde{\Theta}(G/\epsilon^2)$ in the circuit-limited regime. For an arbitrary source $\hat{\rho}$, we introduce the best $G$-gate approximation error $d_G(\hat{\rho})$ and the approximate circuit complexity $C_\eta(\hat{\rho})$. We prove an agnostic quantum Occam theorem: with $M$ copies, one can learn up to the best $G$-gate approximation error plus a statistical penalty $\widetilde{O}(\sqrt{G/M})$. We then remove the need to know $G$ in advance through an adaptive model-selection theorem whose oracle inequality selects the circuit complexity justified by the data. Matching lower bounds yield a sample-supported expressibility law: at trace-distance accuracy $\epsilon$, $M$ samples can support only $G_{\rm supported} \simeq M\epsilon^2$ gates, up to logarithmic factors and tomography saturation at $2^n$. Thus, the circuit complexity becomes an adaptive statistical resource rather than a static promise. Our framework turns bounded circuit complexity into a model-selection principle for quantum machine learning.
toXiv_bot_toot
This is a great accomplishment in machine learning.
I just hate that it's not called this even once in the article and video.
Everything is shoved into the buzzword AI.
But there is no general artificial intelligence here.
It's good old fashioned ML.
https://newatlas.com/robo…
Neural posterior estimation of the neutrino direction in #IceCube using transformer-encoded normalizing flows on the sphere: https://arxiv.org/abs/2604.19846 -> New machine-learning method improves IceCube’s estimation of neutrino direction: https://icecube.wisc.edu/news/research/2026/05/new-machine-learning-method-improves-icecubes-estimation-of-neutrino-direction/
1981 sagte Steve Jobs, Computer seien eine Art Fahrräder für den Geist. Ich habe mir Gedanken gemacht, wie wir generative Machine-Learning-Systeme (GMLS) sehen wollen.
Nachzulesen in meinem Forums-Beitrag von vergangener Woche: https://zenodo.org/records/20029785
The Angle of Attack: What a Hunting Pack Knows About Geometry and What a Machine is Learning to do with It.
A wolf does not charge a moose head-on. It runs toward the place the moose will be, and it arrives there beside other wolves who each compute that same future from a different spot on the field....
welp.
#footiMac remains in a state. If you are reading this, that is a small victory :)
I tried a few things but it remains burdened by I/O activity.
it was still overwhelmed even when I shut down mastodon and nginx so I think it is either the constant sftp traffic or something related to the update to Trixie that I am as yet unaware of.
Regardless, I am taking the opportunity to create docker containers on another machine for postgres and redis to live on.
I'm now waiting for a database dump to complete so that I can try migrating those services over and leaving footiMac to only do nginx and sidekiq
Probably work on it some more tomorrow. Until then this account will be up and down. But at least I'm learning and that's what I like to do.
#mastoadmin
Amazon Web Services (AWS), said customers using its EC2 Capacity Blocks for Machine Learning service will face hourly price increases of around 20% from July.
https://www.computing.co.uk/news/2026/aws-
Crosslisted article(s) found for math.AT. https://arxiv.org/list/math.AT/new
[1/1]:
- RTD-Lite: Scalable Topological Analysis for Comparing Weighted Graphs in Learning Tasks
Eduard Tulchinskii, Daria Voronkova, Ilya Trofimov, Evgeny Burnaev, Serguei Barannikov
https://arxiv.org/abs/2503.11910 https://mastoxiv.page/@arXiv_csLG_bot/114182227105908009
- Hallucination Detection in LLMs with Topological Divergence on Attention Graphs
Alexandra Bazarova, et al.
https://arxiv.org/abs/2504.10063 https://mastoxiv.page/@arXiv_csCL_bot/114340822288698487
- Arithmetic Wu Formulas and the Generalized Hecke Theorem
Shachar Carmeli, Mark Shusterman, Sa'ar Zehavi
https://arxiv.org/abs/2606.06008 https://mastoxiv.page/@arXiv_mathNT_bot/116696438874436734
- $p$-adic Bi-Filtrations for Topological Machine Learning on Genomic Sequences
Tirtharaj Dash, Gunja Sachdeva
https://arxiv.org/abs/2606.06117 https://mastoxiv.page/@arXiv_qbioQM_bot/116696454797742926
- RedZeD: Computing persistent homology by Reduction to Zero Differentials
Chris Kapulkin, Nathan Kershaw
https://arxiv.org/abs/2606.06310 https://mastoxiv.page/@arXiv_csCG_bot/116696326602622617
toXiv_bot_toot
One thing I'm seeing more of is someone arguing that "Artificial Intelligence" only refers to Large Language Models such as ChatGPT and Gemini, and not anything else.
I grant that in 2026, maybe that is how laypeople use the term.
However, AI is a broad umbrella. Example: many include supervised machine learning models such as linear regression and decision trees, even though those are deterministic algorithms to produce a result.
Visibility nowcasting in South Korea: a machine learning approach to class imbalance and distribution shift
Bong Gyun Shin, Chan Sik Lee, Hyesun Suh
https://arxiv.org/abs/2605.21507 https://arxiv.org/pdf/2605.21507 https://arxiv.org/html/2605.21507
arXiv:2605.21507v1 Announce Type: new
Abstract: Atmospheric visibility is a critical variable for transportation safety and air quality management, however, accurate prediction remains challenging due to the complex interactions between meteorological conditions and air pollutants, as well as the rarity of low-visibility events. This study introduces a machine learning framework to nowcast visibility in six major South Korean cities. To handle the imbalance in the 2018-2020 training data, we applied the Synthetic Minority Over-sampling Technique with Nominal and Continuous (SMOTENC) and Conditional Tabular Generative Adversarial Network (CTGAN). An ensemble approach combining machine learning and deep learning models was then used and evaluated on a 2021 test dataset. The results revealed a marked decline in predictive performance in the test set compared to the cross-validation phase. This degradation was attributed to a distributional shift between training and testing periods, which was quantitatively confirmed by measuring the Wasserstein distance of the most influential feature identified by SHAP analysis. In general, this study presents a methodology that aims to simultaneously address the dual challenges of data imbalance and temporal distributional shifts, and emphasizes the necessity of accounting for evolving external environmental factors when implementing nowcasting models on time-series data.
toXiv_bot_toot
Replaced article(s) found for eess.AS. https://arxiv.org/list/eess.AS/new
[1/1]:
- Unifying Diarization, Separation, and ASR with Multi-Speaker Encoder
Muhammad Shakeel, Yui Sudo, Yifan Peng, Chyi-Jiunn Lin, Shinji Watanabe
https://arxiv.org/abs/2508.20474 https://mastoxiv.page/@arXiv_eessAS_bot/115110974009150613
- CALM: Joint Contextual Acoustic-Linguistic Modeling for Personalization of Multi-Speaker ASR
Muhammad Shakeel, Yosuke Fukumoto, Chikara Maeda, Chyi-Jiunn Lin, Shinji Watanabe
https://arxiv.org/abs/2601.22792 https://mastoxiv.page/@arXiv_eessAS_bot/116000207024295325
- How Much Does Machine Identity Matter in Anomalous Sound Detection at Test Time?
Kevin Wilkinghoff, Keisuke Imoto, Zheng-Hua Tan
https://arxiv.org/abs/2602.16253 https://mastoxiv.page/@arXiv_eessAS_bot/116096185732811365
- LMU-Based Sequential Learning and Posterior Ensemble Fusion for Cross-Domain Infant Cry Classific...
Niloofar Jazaeri, Hilmi R. Dajani, Marco Janeczek, Martin Bouchard
https://arxiv.org/abs/2603.02245 https://mastoxiv.page/@arXiv_eessAS_bot/116169771215037748
- Adapting a Text-to-Audio Model for Room Impulse Response Generation
Kirak Kim, Sungyoung Kim
https://arxiv.org/abs/2603.09708 https://mastoxiv.page/@arXiv_eessAS_bot/116209762413602825
- Repurposing Image Diffusion Models for Training-Free Music Style Transfer on Mel-spectrograms
Heehwan Wang, Joonwoo Kwon, Sooyoung Kim, Jungwoo Seo, Shinjae Yoo, Yuewei Lin, Jiook Cha
https://arxiv.org/abs/2411.15913 https://mastoxiv.page/@arXiv_csSD_bot/113548024475383386
- DeePen: Penetration Testing for Audio Deepfake Detection
M\"uller, Kawa, Stan, Doan, Jung, Choong, Sperl, B\"ottinger
https://arxiv.org/abs/2502.20427 https://mastoxiv.page/@arXiv_csCR_bot/114097333876265997
- Re-evaluating Minimum Bayes Risk Decoding for Automatic Speech Recognition
Yuu Jinnai
https://arxiv.org/abs/2510.19471 https://mastoxiv.page/@arXiv_csCL_bot/115422969877240889
- Aliasing-Free Neural Audio Synthesis
Yicheng Gu, Junan Zhang, Chaoren Wang, Jerry Li, Zhizheng Wu, Lauri Juvela
https://arxiv.org/abs/2512.20211 https://mastoxiv.page/@arXiv_csSD_bot/115773521971327576
- TiCo: Time-Controllable Spoken Dialogue Model
Kai-Wei Chang, Wei-Chih Chen, En-Pei Hu, Hung-yi Lee, James Glass
https://arxiv.org/abs/2603.22267 https://mastoxiv.page/@arXiv_csCL_bot/116283643505371784
toXiv_bot_toot
A Next-Generation Snow Albedo Parameterization for Climate Modeling using Constrained Machine Learning
Andrew Charbonneau, Katherine Deck, Tapio Schneider
https://arxiv.org/abs/2606.05419
New research out of Germany’s Karlsruhe Institute of Technology found that the types of Wi-Fi routers we all have in our homes
come with a major privacy vulnerability that can be used to identify any human body that comes within their range.
The study, flagged by Gizmodo, used machine learning systems to identify individuals with an accuracy rate of 99.5 percent.
To do so, the researchers exploited a vulnerability in a process known as beamforming feedback information (BFI),…
Crosslisted article(s) found for physics.atom-ph. https://arxiv.org/list/physics.atom-ph/new
[1/1]:
- Machine-Learning Optimization and Characterization of a High-Optical-Depth Two-Color Nanofiber Trap
W. Crump, M. Sadeghi, M. D. Hoogerland
Decentralized Machine Learning with Centralized Performance Guarantees via Gibbs Algorithms
Yaiza Bermudez, Samir Perlaza, I\~naki Esnaola
https://arxiv.org/abs/2604.20492 https…
The DOD seeks to recruit engineers experienced in frontier AI, machine learning and automation, and data systems, to embed them "down to the unit level" (John Harney/Bloomberg)
https://www.bloomberg.com/news/articles/20
#AI to recreate F/OSS in a "clean room" without acknowledging that it trained on F/OSS takes copyright evasion to an uncomfortable new level.
To anybody actually versed in machine learning, this …
Replaced article(s) found for physics.geo-ph. https://arxiv.org/list/physics.geo-ph/new
[1/1]:
- Regimes of rotating convection in an experimental model of the Earth's tangent cylinder
Rishav Agrawal, Martin Holdsworth, Alban Poth\'erat
https://arxiv.org/abs/2408.07837 https://mastoxiv.page/@arXiv_physicsgeoph_bot/112970809988434109
- Machine learning enhanced data assimilation framework for multiscale carbonate rock characterization
Bo, Elsheikh, Menke, Maes, Geiger, Kashim, Bakar, Singh
https://arxiv.org/abs/2602.06989 https://mastoxiv.page/@arXiv_physicsgeoph_bot/116045261443672160
- Guided Unconditional and Conditional Generative Models for Super-Resolution and Inference of Quas...
Anantha Narayanan Suresh Babu, Akhil Sadam, Pierre F. J. Lermusiaux
https://arxiv.org/abs/2507.00719 https://mastoxiv.page/@arXiv_physicsfludyn_bot/114782990520242000
- PCP-GAN: Property-Constrained Pore-scale image reconstruction via conditional Generative Adversar...
Ali Sadeghkhani, Brandon Bennett, Masoud Babaei, Arash Rabbani
https://arxiv.org/abs/2510.19465 https://mastoxiv.page/@arXiv_csCV_bot/115422929244004682
- Fate of Secondary Droplets Produced by High-speed Raindrops Interacting with a Liquid Pool
Han-Hsiang Kuo, Xuanting Hao
https://arxiv.org/abs/2604.10491 https://mastoxiv.page/@arXiv_physicsfludyn_bot/116402146676519672
- Excursion-set structure factor of the auroral electric field
Magnus F Ivarsen, Kaili Song, Jean-Pierre St-Maurice, Glenn C Hussey
https://arxiv.org/abs/2606.26854 https://mastoxiv.page/@arXiv_physicsspaceph_bot/116815350546290631
toXiv_bot_toot
Conditional Normalizing Flow for Gas-Surface Scattering from Thermal to Hypersonic Velocities
Miklas Sch\"utte, Stephen Hocker, Hansj\"org Lipp, Johannes Roth, Stefanos Fasoulas, Marcel Pfeiffer
https://arxiv.org/abs/2606.31928 https://arxiv.org/pdf/2606.31928 https://arxiv.org/html/2606.31928
arXiv:2606.31928v1 Announce Type: new
Abstract: Accurate aerodynamic modeling of satellites in very low Earth orbit (VLEO) requires gas-surface interaction (GSI) models that capture the full velocity spectrum from thermal to orbital speeds. Atmospheric particles initially strike spacecraft surfaces at hypersonic velocities of 6 000 - 10 000 m/s. Due to surface roughness and complex geometries, especially within air-breathing electric propulsion (ABEP) intake systems, multiple collisions occur, progressively reducing the particle velocities. A recent machine learning framework for deriving scattering kernels from molecular dynamics (MD) simulations has shown promise, but remains limited to high-velocity single impacts and possibly violates fundamental equilibrium principles such as detailed balance. This work extends this machine learning based scattering kernel to cover the complete velocity range using conditional normalizing flows trained with physics-informed constraints, enabling accurate modeling of multi-bounce scenarios in realistic VLEO applications. We train a conditional Real-valued Non-Volume Preserving (cRealNVP) model on expanded molecular dynamics simulations covering velocities from thermal to hypersonic speeds, incorporating a detailed balance loss term. The resulting model demonstrates improved accuracy compared to previous approaches even in the original high-velocity regime, while successfully capturing thermal-velocity scattering. Quantitative assessment shows that thermalization is approximated within acceptable tolerances. This framework provides essential capabilities for accurate ABEP intake optimization and VLEO mission planning while offering a general methodology applicable to broader rarefied gas dynamics problems requiring thermodynamic consistency.
toXiv_bot_toot
[2026-06-22 Mon (UTC), no new articles found for cs.LG Machine Learning]
toXiv_bot_toot
[2026-04-24 Fri (UTC), 10 new articles found for stat.ML Machine Learning]
toXiv_bot_toot
Commure, which offers AI, revenue cycle management, and workflow automation tools for healthcare providers, raised $70M led by GC at a $7B post-money valuation (Paige Minemyer/Fierce Healthcare)
https://www.fiercehealthcare.com/ai-and-ma
A differentiable machine learning small-angle X-ray scattering analysis framework for structure elucidation of lipid nanoparticles
Maria B{\aa}nkestad, Sandra Barman, Magnus R\"oding, Erik Kaunisto, Viktoriia Meklesh, Audrey Gallud, Marco Mendez, Marianna Yanez Arteta, Stefan Norberg, Ann Terry, Smita Chakraborty, Shun Yu, Jerk R\"onnols, Sepideh Pashami
Visibility nowcasting in South Korea: a machine learning approach to class imbalance and distribution shift
Bong Gyun Shin, Chan Sik Lee, Hyesun Suh
https://arxiv.org/abs/2605.21507
Are you an MSc student looking for a thesis topic? Interested in Greenland/Antarctica atmosphere and ice sheet processes? Background in meteorology, geography, earth science or physics (or other quantitative discipline?
Then do I have the project for you...
I have just updated my list of open research ideas here:
#MScThesis #AcademicChatter #Greenland #Antarctica #ClimateChange #Meteorology #Wx #Glaciology #MachineLearning #ClimateModelling
A Scoping Review of Physics Informed Machine Learning for Wave Propagation Modeling in Seismology
\'Oscar Rinc\'on-Carde\~no, Gregorio P\'erez-Bernal, Silvana Montoya-Noguera, Nicol\'as Guar\'in-Zapata
https://arxiv.org/abs/2607.00178
JAX-SCM v1.0: a modern atmospheric single-column model for boundary layer research
Maximilian Pierzyna
https://arxiv.org/abs/2605.24544 https://arxiv.org/pdf/2605.24544 https://arxiv.org/html/2605.24544
arXiv:2605.24544v1 Announce Type: new
Abstract: We present JAX-SCM v1.0, an open-source atmospheric single-column model for boundary layer research, implemented in Python using the JAX computing library. The model solves for horizontal wind, potential temperature, and specific humidity, combined with prognostic turbulent kinetic energy and turbulent statistics parameterized by the Mellor-Yamada-Nakanishi-Niino level-2.5 (MYNN-2.5) turbulence closure. We verify the implementation against three well-established benchmark cases covering neutral (turbulent Ekman layer), stable (GABLS1), and convective (Wangara Day 33) conditions. Close agreement with reference solutions is demonstrated across all regimes. By building on JAX, the model benefits from just-in-time compilation and native GPU support. While JAX-SCM is not yet fully differentiable, basing it on JAX also lays the foundation for future integration with machine learning components. The model is designed for simplicity and modularity, lowering the barrier to entry for users and developers alike.
toXiv_bot_toot
Crosslisted article(s) found for physics.comp-ph. https://arxiv.org/list/physics.comp-ph/new
[1/1]:
- From Local Training to Large-Scale Mapping: A Comparative Assessment of Machine Learning and Deep...
Hsiao-Jou Hsu, Joachim Moortgat
Crosslisted article(s) found for physics.comp-ph. https://arxiv.org/list/physics.comp-ph/new
[1/1]:
- Hybrid Two-Level Transport Method with Solution Decomposition in Macro and Micro Components
Caleb A. Shaw, Dmitriy Y. Anistratov
https://arxiv.org/abs/2607.01346 https://mastoxiv.page/@arXiv_mathNA_bot/116854910030264363
- Predicting Novel Stable Materials for Experimental Synthesis
Yuqi An, Sihong Zhu, Joseph Montoya, Xingyu Guo, Zhenbin Wang
https://arxiv.org/abs/2607.01713 https://mastoxiv.page/@arXiv_condmatmtrlsci_bot/116854978846171607
- An Optimisation Framework for the Well-Conditioned Training of Physics-Informed Neural Networks
Joseph Webb, Sadok Jerad, Coralia Cartis
https://arxiv.org/abs/2607.02194 https://mastoxiv.page/@arXiv_csLG_bot/116855143607520453
- Efficient Large-Scale STEM-EELS Simulations With Torched-TACAW
Martin Osmera, Jo\~ao Vaz, Paul M. Zeiger, J\'an Rusz
https://arxiv.org/abs/2607.02236 https://mastoxiv.page/@arXiv_condmatmtrlsci_bot/116855081674592173
- Grounded autonomous research: a fault-tolerant LLM pipeline from corpus to manuscript in frontier...
Haonan Huang
https://arxiv.org/abs/2607.02329 https://mastoxiv.page/@arXiv_csAI_bot/116855126306616827
- Beyond Adam: SOAP and Muon for Faster, Label-Efficient Training of Machine Learning Interatomic P...
Harari, Zimmermann, Kulseng, Zichi, Tan, Descoteaux, Kozinsky
https://arxiv.org/abs/2607.02499 https://mastoxiv.page/@arXiv_csLG_bot/116855152847861336
toXiv_bot_toot
Replaced article(s) found for physics.ao-ph. https://arxiv.org/list/physics.ao-ph/new
[1/1]:
- Smoothing and spatial verification of global fields
Gregor Skok, Katarina Kosovelj
https://arxiv.org/abs/2412.00936 https://mastoxiv.page/@arXiv_physicsaoph_bot/113587890587543610
- Radiosonde-constrained reconstructions reveal a weakening Northern Hadley circulation
Matic Pikovnik, \v{Z}iga Zaplotnik
https://arxiv.org/abs/2503.05331 https://mastoxiv.page/@arXiv_physicsaoph_bot/114137034331234752
- Non-stationary time series attribution for heatwaves over Europe
Pascal Meurer, Sebastian Buschow, Svenja Szemkus, Petra Friederichs
https://arxiv.org/abs/2601.05841 https://mastoxiv.page/@arXiv_physicsaoph_bot/115881278944409798
- Enabling High-Accuracy Data Assimilation with Limited Ensembles via Machine Learning-Based Covari...
Zhou Yao, Zhilin Li, Li Zhao, Zeng Liu, Zhaokuan Lu, Seungnam Kim, Guangyao Wang
https://arxiv.org/abs/2605.11639 https://mastoxiv.page/@arXiv_physicsaoph_bot/116566237831166337
toXiv_bot_toot
RE: https://mastodonapp.uk/@JohnSullivan/116842603611650876
“Some of the company’s most experienced personnel left before all of their accumulated knowledge could be fully transferred into Ford’s automated systems…”
This is apparently the new line for blaming companies for AI failures: you didn’t fully upload the brains of your senior people before firing them! You have to complete the extraction process first! Suck them dry, •then• discard them!
Machine learning does not actually work that way, but…in this FOMO-driven industry, anything goes to blame the customer.
🧵
@inthehands@hachyderm.io
![Company
About Us
Our Robots
Blog
Offshore Offices
Legal
Terms of Service
Privacy Policy
MalusCorp-0 License
Indemnification Waiver
© 2024 MalusCorp International Holdings Ltd. Registered in [JURISDICTION WITHHELD].
This service is provided "as is" without warranty. MalusCorp is not responsible for any legal consequences, moral implications, or late-night guilt spirals resulting from use of our services.](https://media.infosec.exchange/infosec.exchange/media_attachments/files/116/658/451/278/743/528/original/d61f29cb66264482.jpg)
