Basin

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, down 40% on the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 23

All topics

Learning Physics from an Imperfect Ancestor
Sep 21, 2026S. Mohammad Mousavi, Teeratorn Kadeethum, Nikolaos Bouklas +1Parametric Physics-Informed Neural Network Partial Differential Equations
Sibley School of Mechanical and Aerospace Engineering, Cornell University · AI Lab, Siemens Energy · Department of Civil and Systems Engineering, Johns Hopkins University
The Answer-Basin Representation Hypothesis: We Are Not Probing or Steering Concepts
Sep 21, 2026Manjiang Yu, Hongji Li, Zihan Wang +5Hypothesis Basin
The University of Queensland · Mohamed bin Zayed University of Artificial Intelligence · Institute of Science Tokyo
Ranking Competing geologic interpretations via foundation-model-assisted generative hydrologic inversion
Sep 17, 2026Harun Ur Rashid, Daniel O'MalleyGeological Semantic Understanding Probabilistic Basin-Scale Runoff Lstms
Earth and Environmental Sciences Division, Los Alamos National Laboratory, Los Alamos, NM, USA
Basin Geometry and Reliable Recall of Dynamical Memories in Reservoir Computing
Sep 1, 2026Ling-Wei Kong, Ying-Cheng LaiReservoir Computing Dense Associative Memory
Department of Computational Biology, Cornell University, Ithaca, NY 14850, USA · School of Electrical, Computer, and Energy Engineering, Arizona State University, Tempe, AZ 85287, USA · Department of Physics, Arizona State University, Tempe, Arizona 85287, USA
Escaping Reasoning Basin Collapse with History-Biased Search
Sep 1, 2026Lu ChengInference-Time Reasoning Paths
Department of Computer Science University of Illinois Chicago Chicago, IL 60607
Basins of Attraction to Multiple Fixed Points in Discrete-time Hysteresis Neural Networks
Aug 24, 2026Yuta Arai, Seigo Nakamura, Ryoga Nakamura +2Basin Fixed-Point Iteration
Hosei University, Koganei, Tokyo, Japan
Making Every Step Count: Spatio-Temporal Information Allocation for Imaging Inverse Problems
Aug 12, 2026Yi Cao, Xiangyong Cao, Pei Liu +2Bayesian Inverse Problems Contrastive Flow Matching
Xi’an Jiaotong University · Tsinghua University
Basin: Efficient and Extensible Numerical Optimization in Rust
Aug 11, 2026Johan LarssonBasin Constrained Optimization
Department of Mathematical Sciences, University of Copenhagen, Denmark
Score-Based Stabilization for Time-Dependent Problems
Jul 27, 2026Eshed Gal, Eldad Haber, Uri AscherBasin
University of British Columbia Vancouver, British Columbia, Canada
Revisiting the Volume Hypothesis
Jun 30, 2026Ari Pakman, Lior Kreimer, Yakir BerchenkoStochastic Gradient Descent Basin
Department of Industrial Engineering and Management, Ben-Gurion University of the Negev, Beer Sheva, Israel.
Reconstructing GRACE Terrestrial Water Storage with Spatio-Temporal Graph Neural Networks: An Application to South America
Jun 22, 2026Lukas Arzoumanidis, Lara Johannsen, Klara Middendorf +2Temporal Graph Neural Networks Neural Network
HafenCity University, Computational Methods Lab Hamburg, Germany · HafenCity University, Geodesy and Adjustment Theory Hamburg, Germany · GFZ Helmholtz Centre for Geosciences, Global Geomonitoring and Gravity Field Potsdam, Germany
MSC-CMA-ES: Structure-Aware Restarts for CMA-ES via Cyclic Nearest-Better Basin Discovery
Jun 14, 2026Dimitar Nedanovski, Svetoslav Nenov, Dimitar PilevMetaheuristics Basin
Faculty of Mathematics and Informatics Sofia University St. Kliment Ohridski James Baucher Blvd., 1164 Sofia, Bulgaria · Department of Mathematics University of Chemical Technology and Metallurgy Sofia, Bulgaria · Department of Informatics University of Chemical Technology and Metallurgy Sofia, Bulgaria
Continuous Language Diffusion as a Decoder-Interface Problem
Jun 7, 2026Zhicheng Du, Lan MaDiffusion Language Models Latent Diffusion Model
Tsinghua Shenzhen International Graduate School, Tsinghua University
Convex Basins in Single-Index Model Loss Landscapes: Applications to Robust Recovery under Strong Adversarial Corruption
May 28, 2026Santanu Das, Sagnik Chatterjee, Jatin BatraAnisotropic Loss Landscapes Basin
School of Technology and Computer Science, Tata Institute of Fundamental Research, Mumbai, India.
Detecting Metastable Basins in High Dimensions via Marginal Trajectory Distribution Discrimination
May 22, 2026Taj Jones-McCormickMetastable Samples Basin
Same Target, Different Basins: Hard vs. Soft Labels for Annotator Distributions
May 20, 2026Mirerfan Gheibi, Gashin GhazizadehLabel Propagation Human Annotators
Independent Researcher.
Proximal basin hopping: global optimization with guarantees
May 18, 2026Guillaume Lauga, Cesare Molinari, Samuel VaiterProximal Operators Flat Minima
LJAD · LJAD Université Côte d’Azur France · MaLGA +3
Mapping the Fitness Landscape: A Structure-Guided Approach to Multi-Modal Optimization
May 18, 2026Meng Xiang, Pei YanOptimization Landscape Evolutionary Optimization
University of Aizu Aizuwakamatsu, Japan
Equilibrium Selection in Multi-Agent Policy Gradients via Opponent-Aware Basin Entry
May 18, 2026Yevhen Shcherbinin, Arina Redina, Maxim Kalpin +1Nash Equilibrium Equilibrium
Bloomsbury Technology, London, United Kingdom · London School of Economics and Political Science, London, United Kingdom · University of Bristol, Bristol, United Kingdom +2
Drain-Vortex Optimization: A Population-Based Metaheuristic Inspired by Multi-Drain Free-Vortex Flow
May 9, 2026Mohsen Omidi, Brian VaughanMetaheuristics Basin
Technological University Dublin, Grangegorman Lower, Dublin, D07 C972, Ireland
Attractor Geometry of Transformer Memory: From Conflict Arbitration to Confident Hallucination
May 7, 2026Qiyao Liang, Risto Miikkulainen, Ila FieteHidden States Large Language Models Fail
Massachusetts Institute of Technology · University of Texas Austin, Cognizant · Cognizant
ImprovEvolve: Basin-Hopping Meets LLM-Guided Evolutionary Search
Feb 10, 2026Alexey Kravatskiy, Valentin Khrulkov, Ivan OseledetsEvolutionary Search Alphaevolve
1MIRIAI, Russia · 2FusionBrain Lab, Russia · 3AXXX, Russia +1
Utilizing Earth Foundation Models to Enhance the Simulation Performance of Hydrological Models with AlphaEarth Embeddings
Jan 4, 2026Pengfei Qu, Wenyu Ouyang, Chi Zhang +6Probabilistic Basin-Scale Runoff Lstms Basin
School of Computer Science and Technology, Dalian University of Technology, Dalian, China · School of Infrastructure Engineering, Dalian University of Technology, Dalian, China · School of Information and Communication Engineering, Dalian University of Technology, Dalian, China +2

Sep 21, 2026, cs.LGJ/K move · Enter open · S save

Learning Physics from an Imperfect Ancestor

S. Mohammad Mousavi, Teeratorn Kadeethum, Nikolaos Bouklas, Somdatta Goswami

Sibley School of Mechanical and Aerospace Engineering, Cornell University · AI Lab, Siemens Energy · Department of Civil and Systems Engineering, Johns Hopkins University

Parametric Physics-Informed Neural Network Partial Differential Equations Basin

Open paper AskPDF arXiv

Neural operators evaluate parametric partial differential equations cheaply but degrade sharply outside their training distribution. Physics-informed neural networks avoid dependence on labeled data, yet their optimization can be basin-fragile: when the governing residual admits multiple solutions, a PINN trained from scratch may converge to a physically incorrect state despite achieving a small residual. We show that these failure modes can be addressed jointly: an imperfect NO provides the structural prior needed to place a PINN in the correct solution basin, while the PDE residual refines the solution beyond the operator's accuracy. We introduce a three-stage framework that freezes the spatial basis of a physics-informed NO, extrapolates its solution branch to an out-of-distribution parameter using a polynomial continuation prior, and distills the resulting field into a fresh PINN. The NO need not be accurate at the target; it transfers solution-branch information, while PDE residual minimization in the PINN governs convergence. We evaluate the framework on three nonlinear PDEs: 1D viscous Burgers, 2D steady Allen-Cahn near a pitchfork bifurcation, and 2D steady lid-driven cavity flow. For Allen-Cahn, where the trivial solution satisfies the PDE residual exactly, a standard PINN collapses to the trivial zero branch, whereas distillation from the crude extrapolated operator recovers the non-trivial branch that matches the finite-difference reference. For the lid-driven cavity, extrapolating to a Reynolds number of Re = 3200 accelerates convergence to the correct physical state, achieving competitive accuracy using fewer parameters and optimization steps than recent literature baselines. These results establish a simple principle: an NO need not accurately predict the solution to be useful; it only needs to identify the correct basin from which PINN optimization can recover it.

Momentum

Related topics

Latest papers 23