{"total":15,"items":[{"citing_arxiv_id":"2607.07385","ref_index":12,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"JAX-FVM: A differentiable, entropy-stable finite volume solver on unstructured meshes for compressible flows","primary_cat":"math.NA","submitted_at":"2026-07-08T13:17:00+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":6.0,"formal_verification":"none","one_line_summary":"JAX-FVM is a differentiable, entropy-stable finite volume solver for 2D compressible Euler/Navier-Stokes equations on unstructured meshes, built in JAX.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.27895","ref_index":33,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Mosaic: A Benchmark Suite for Differentiable Physics Solvers","primary_cat":"physics.comp-ph","submitted_at":"2026-06-26T09:38:33+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Mosaic is a benchmark suite evaluating 14 differentiable PDE solvers across fluids, structures, and heat transfer, showing large variations in cost and conditioning but similar convergence behavior.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.11691","ref_index":26,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Spectrally Regularized Latent Flow Matching for Turbulence Generation","primary_cat":"cs.LG","submitted_at":"2026-06-10T06:09:51+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Spectrally regularized compression in latent flow matching raises retained deep-dissipation spectral power from 20% to 79% in generated turbulence on a 256^2 DNS dataset at Re_f ≈ 2250.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.10335","ref_index":63,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"A Physics-Informed B-Spline Framework for Continuous Approximation of Flow Data","primary_cat":"physics.comp-ph","submitted_at":"2026-06-09T02:29:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"PI-MFA optimizes tensor-product B-spline control points to balance data fidelity against PDE residuals, producing physically consistent continuous flow fields.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.09001","ref_index":18,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"JAX-AMG: A GPU-Accelerated Differentiable Sparse Linear Solver Library for JAX","primary_cat":"cs.MS","submitted_at":"2026-06-08T03:57:19+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A new JAX library provides GPU-accelerated AMG-preconditioned sparse linear solves with reverse-mode automatic differentiation, JIT, and MPI support.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.07481","ref_index":24,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Drifting Models for Surrogate Flow Modeling","primary_cat":"cs.LG","submitted_at":"2026-06-05T17:35:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A label-conditioned drifting model in VAE latent space matches diffusion accuracy for flow surrogates while running two orders of magnitude faster, with a spatial variant for unseen geometries.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.05371","ref_index":18,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Mamba-Assisted Non-Markovian Closure for Reduced-Order Modeling","primary_cat":"cs.LG","submitted_at":"2026-06-03T19:18:50+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Mamba-Assisted Closure (MAC) trains a Mamba sequence model on resolved trajectories to predict non-Markovian closures and couples it with reduced-order equations, outperforming Markovian, GRU, and Wilks baselines on Burgers' and Lorenz '96 systems.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.25353","ref_index":2,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"PDEInvBench: A Comprehensive Dataset and Design Space Exploration of Neural Networks for PDE Inverse Problems","primary_cat":"cs.LG","submitted_at":"2026-05-25T02:13:33+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"PDEInvBench supplies a new benchmark dataset for PDE inverse problems and shows that two-stage supervised-plus-test-time training, PDE derivative inputs, and diverse initial conditions improve neural network accuracy on parameter recovery.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.22222","ref_index":22,"ref_count":3,"confidence":0.88,"is_internal_anchor":false,"paper_title":"ARC-STAR: Auditable Post-Hoc Correction for PDE Foundation Models","primary_cat":"cs.LG","submitted_at":"2026-05-21T09:26:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"ARC-STAR reduces velocity rollout error by at least 36x over raw Poseidon across all tested regime cells via auditable global and local correction stages on five flow benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.19589","ref_index":14,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Physics-Informed Graph Neural Network Surrogates for Turbulent Nanoparticle Dispersion in Dental Clinical Environments","primary_cat":"cs.LG","submitted_at":"2026-05-19T09:31:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"ELGIN is a graph-based physics-informed surrogate model that predicts carrier flow and polydisperse particle motion in dental aerosol scenarios, achieving lower tracking errors and 37x speedup versus full OpenFOAM CFD in a preliminary single-case test.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"is the predicted residual increment from the network with parametersθ. The increment is produced by an EPD network whose processor is a stack ofKE =4 multi-head graph-transformer blocks with Hatt =4 heads each; node updates use small multi-layer perceptron (MLP) maps denoted MLP (k) n below. α (k,h) i j =softmax j∈N(i) W (k,h) Q h(k) i \u0001⊤ W (k,h) K h(k) j +W (k,h) E e(k) i j \u0001 p dh/Hatt ,(14) h(k+1) i =h (k) i +MLP (k) n \u0010 Hatt h=1 ∑ j∈N(i) α (k,h) i j W (k,h) V h(k) j \u0011 ,(15) with hidden dimensiond h =64, residual connections and layer normalisation. Hereh (k) i is the Eulerian node embedding,e (k) i j the edge feature on the owner-neighbour link(i,j)onG E, 9 W (k,h) Q ,W (k,h) K ,W (k,h) V , andW (k,h) E are learnable attention projections for headh,α (k,h)"},{"citing_arxiv_id":"2605.11111","ref_index":8,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"ShardTensor: Domain Parallelism for Scientific Machine Learning","primary_cat":"cs.DC","submitted_at":"2026-05-11T18:20:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"ShardTensor is a domain-parallelism system for SciML that enables flexible scaling of extreme-resolution spatial datasets by removing the constraint of batch size one per device.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"INTRODUCTION Scientific machine learning applications have become a vehicle for accelerated simulation, scientific discovery, and industrial design. Machine learning has found applications in an incredible breadth of domains: healthcare and medicine [1], [2], industrial design [3]-[5], fluid dynamics [6] and aerodynamics [7], weather and climate forecasting [8], [9], fundamental sciences [10]-[12], and many, many more [13]- [15]. It is not an overstatement to say that machine learning methods are fundamentally changing scientific research, all the way from early development to end user and industrial applications. Scientific data has several attributes that make it especially challenging to use for both training and inference, leading to"},{"citing_arxiv_id":"2605.00462","ref_index":6,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Adaptation of AI-accelerated CFD Simulations to the IPU platform","primary_cat":"cs.DC","submitted_at":"2026-05-01T06:53:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"Porting AI-accelerated CFD model training to IPU-POD16 yields 34% data-feeding speedup and scales throughput to 2805 samples/s on 16 IPUs despite inter-IPU communication limits.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.19355","ref_index":34,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"LASER: Learning Active Sensing for Continuum Field Reconstruction","primary_cat":"cs.LG","submitted_at":"2026-04-21T11:36:09+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":6.0,"formal_verification":"none","one_line_summary":"LASER couples a latent world model with a GRPO-trained RL policy to adaptively reposition sensors for sparse continuum field reconstruction, outperforming fixed and offline-optimized placement strategies across PDE and real-world benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.06881","ref_index":6,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"MENO: MeanFlow-Enhanced Neural Operators for Dynamical Systems","primary_cat":"cs.LG","submitted_at":"2026-04-08T09:39:49+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"MENO restores multi-scale structure in neural-operator PDE surrogates via one-step improved MeanFlow, claiming up to 2× better power-spectrum accuracy and up to 14× faster inference than DDIM enhancement.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2507.19861","ref_index":136,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Quantum-Informed Machine Learning for Predicting Spatiotemporal Chaos with Practical Quantum Advantage","primary_cat":"quant-ph","submitted_at":"2025-07-26T08:36:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"QIML uses a quantum-trained Q-Prior to enhance classical autoregressive predictions of spatiotemporal chaos, improving accuracy by up to 17.25% and full-spectrum fidelity by up to 29.36% while enabling stable forecasts for 3D turbulent channel flow.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}