arXiv:2505.11211v3 Announce Type: replace Abstract: We propose Bayesian Hierarchical Invariant Prediction (BHIP) reframing Invariant Causal Prediction (ICP) through the lens of Hierarchical Bayes. We leverage the hierarchical structure to explicitly test invariance of causal mechanisms under heterogeneous data, resulting in…
arXiv:2604.03463v1 Announce Type: new Abstract: In highly interactive driving scenes, trajectory prediction is conditioned on information from surrounding traffic participants such as cars and pedestrians. Our main contribution is a comprehensive analysis of state-of-the-art trajectory predictors, which reveals a surprising…
Researchers developed a system that intelligently balances workloads to improve the efficiency of flash storage hardware in a data center.
arXiv:2604.04872v1 Announce Type: cross Abstract: As large language model agents advance beyond software engineering (SWE) tasks toward machine learning engineering (MLE), verifying agent behavior becomes orders of magnitude more expensive: while SWE tasks can be verified via fast-executing unit tests,…
arXiv:2512.18503v3 Announce Type: replace-cross Abstract: Synthetic Aperture Radar (SAR) offers a unique capability for all-weather, space-based maritime activity monitoring by capturing and imaging strong reflections from ships at sea. A well-defined challenge in this domain is ship type classification. Due…
arXiv:2603.29496v2 Announce Type: replace-cross Abstract: We present Metriplector, a neural architecture primitive in which the input configures an abstract physical system — fields, sources, and operators — and the dynamics of that system is the computation. Multiple fields evolve via…
arXiv:2603.28921v2 Announce Type: replace Abstract: Standard neural network training uses constant momentum (typically 0.9), a convention dating to 1964 with limited theoretical justification for its optimality. We derive a time-varying momentum schedule from the critically damped harmonic oscillator: mu(t) =…
arXiv:2506.00721v2 Announce Type: replace-cross Abstract: We present Common Inpainted Objects In-N-Out of Context (COinCO), a novel dataset addressing the scarcity of out-of-context examples in existing vision datasets. By systematically replacing objects in COCO images through diffusion-based inpainting, we create 97,722…
arXiv:2509.20349v2 Announce Type: replace Abstract: Accurate time-series forecasting for complex physical systems is the backbone of modern industrial monitoring and control, yet deep learning models often lack the physical consistency required in regulated environments. To bridge this gap, we introduce…
arXiv:2602.19967v3 Announce Type: replace Abstract: Physics-informed neural networks (PINNs) provide a promising framework for solving inverse problems governed by partial differential equations (PDEs) by integrating observational data and physical constraints in a unified optimization objective. However, the ill-posed nature of…
