arXiv AI
Observation-Aligned Mask Priors for Learning Physical Fields from Authentic Occlusions
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Oct 16
Latent Annealed Posterior Sampling with a Variance-Preserving Bridge for Sparsely Observed Random Fields
The paper introduces Latent Annealed Posterior Sampling (LAPS), a method that maps sparsely observed random fields into a lower‑dimensional latent space and performs posterior sampling there. A variance‑preserving bridge controls local covariance inflation, while flow matching learns the latent prior. Experiments on Gaussian benchmarks, a bimodal posterior, and a Navier‑Stokes field show that LAPS accurately approximates posterior distributions, preserves multiple modes, and keeps conditional sampling costs nearly constant as spatial resolution increases.
arXiv Statistics ML
Oct 28
OneFlowSBI: One Model, Many Queries for Simulation-Based Inference
OneFlowSBI is a masked flow matching framework that trains a single network on the joint distribution of parameters and observations, using a ternary mask to indicate observed, generated, or absent coordinates. This mask-based approach allows any conditional or marginal inference to be performed by simply changing the mask, avoiding the quadratic attention cost of transformer-based generalists. Experiments on high‑dimensional image denoising and shallow water inference show that OneFlowSBI achieves lower posterior error, faster sampling, and can handle missing data without retraining, while matching or exceeding neural posterior estimation on most SBIBM tasks.
arXiv AI
Jul 22
Incomplete Observations Boost Evolutionary Performance in Ocean Modeling
arXiv:2607. 19147v1 Announce Type: cross Abstract: Data-driven methods have revolutionized ocean modeling, yet current approaches rely heavily on complete reanalysis datasets, imposing computational constraints and limiting model performance to that of the training data.
arXiv Machine Learning
Aug 28
TRACE: Retrospective Streaming Generation of Physical Fields under Sparse Structured Sensing
TRACE is a retrospective streaming generative reconstruction framework designed to recover continuous physical fields from sparse, structured sensing streams. It performs approximate Bayesian inference in a continuous-coordinate latent space, fuses sparse off‑grid measurements with a state‑space temporal prior via Kalman‑style filtering, and refines past frames through retrospective smoothing. Experiments on active matter, ocean sound‑speed fields, and supernova simulations demonstrate that TRACE matches or surpasses existing frame‑wise generative reconstructors, offline spatiotemporal methods, and streaming data‑assimilation baselines in reconstruction quality under temporally sparse and spatially localized sensing protocols.
arXiv Machine Learning
Jun 4
Rethinking Incompleteness: Formalizing Protocol Divergence and Train-Once Learning for Robust IMVC
arXiv:2606. 04857v1 Announce Type: new Abstract: Standard IMVC evaluation retrains separate models for different missing-data configurations.
arXiv Machine Learning
Sep 30
Beyond Missing Rates: Rethinking Incomplete Multi-View Clustering with Protocol Divergence
The paper introduces the concept of protocol divergence, showing that identical nominal missing rates can lead to vastly different learning regimes in incomplete multi‑view clustering. It critiques existing evaluation practices that ignore observation structure and proposes CRAFT, a train‑once framework that fuses observed views with mask‑aware attention, enabling efficient deployment across multiple missing‑view protocols. Experiments on CUB, MultiFashion, and other benchmarks demonstrate CRAFT’s superior performance and significant computational savings through checkpoint reuse.