arXiv AI August 24, 2026 By Sakif Hossain, Julian Teusch, J\"org P. M\"uller

SPARC: Single-Pass Scaling for Motion Forecasting with Conformal Bayesian Last Layers

SPARC (Single-Pass Adaptive Risk Calibration) is a Bayesian‑conformal uncertainty layer for human motion forecasting that adds an analytic epistemic scale to a deterministic MLP backbone’s Gaussian covariance. The scale, κ_t(x), inflates the covariance without altering its correlation structure, enabling 95% marginal prediction tubes with finite‑sample validity via split conformal calibration. Across nine dataset‑protocol blocks, SPARC outperforms baselines on NLL and a combined MPJPE+NLL metric while maintaining competitive point accuracy and efficient calibrated tubes.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

multimodal

arXiv Machine Learning

Jul 2

TRIE: An Evaluation Framework for Stochastic PDE Surrogates

arXiv:2607. 00196v1 Announce Type: new Abstract: Many scientific systems exhibit uncertainty from stochastic forcing, unresolved degrees of freedom, or imperfect observations, making reliable surrogate forecasting fundamentally distributional rather than pointwise.

By Bharat Srikishan, Javier E. Santos, Nikhil Muralidhar, Charles D. Young

arXiv Machine Learning

Jun 10

Optimization-based Online Conformal Prediction for Multi-step Forecasting

arXiv:2508. 13362v2 Announce Type: replace Abstract: Conformal prediction (CP) is well-suited for uncertainty quantification in time series forecasting due to its distribution-free coverage guarantees.

By Ruipu Li, Daniel Menacho, Alexander Rodr\'iguez

agents robotics benchmarks

arXiv Machine Learning

Sep 1

Information-Based Calibration of Uncertainty Quantification in Product-of-Experts Gaussian Process Models

arXiv:2608.29349v1 Announce Type: new Abstract: Gaussian process (GP) regression with a single global GP (GP-glo) incurs cubic computational cost, limiting scalability to large datasets. Product-of-e...

By Yean Hoon Ong, Paolo Barucca, Wei Pan, Jun Wang

arXiv Machine Learning

Sep 15

Beyond Point Forecasts: A Survey on Probabilistic Forecasting for Time Series and Spatiotemporal Data

arXiv:2609.13345v1 Announce Type: cross Abstract: Probabilistic forecasting is central to decision-making under uncertainty, yet its methodological landscape has become increasingly fragmented across...

By Donia Besher, Rajdeep Pathak, Madhurima Panja, Tanujit Chakraborty

arXiv Machine Learning

Jul 21

Singular Bayesian Neural Networks

arXiv:2602. 00387v4 Announce Type: replace-cross Abstract: Bayesian neural networks promise calibrated uncertainty but require $O(mn)$ parameters for standard mean-field Gaussian posteriors.

By Mame Diarra Toure, David A. Stephens

llms benchmarks safety

arXiv Computer Vision

Sep 1

Uncertainty-Aware Trajectory Forecasting from Imperfect Tracking

arXiv:2608.30899v1 Announce Type: new Abstract: Most trajectory forecasting models are trained on clean annotated histories, and are often evaluated under the same idealized assumption, although prac...

By Stephane Da Silva Martins, Victor Petrovic, Emanuel Aldea, Sylvie Le H\'egarat-Mascle

efficiency

One email a morning, machine-written

Related stories

TRIE: An Evaluation Framework for Stochastic PDE Surrogates

Optimization-based Online Conformal Prediction for Multi-step Forecasting

Information-Based Calibration of Uncertainty Quantification in Product-of-Experts Gaussian Process Models

Beyond Point Forecasts: A Survey on Probabilistic Forecasting for Time Series and Spatiotemporal Data

Singular Bayesian Neural Networks

Uncertainty-Aware Trajectory Forecasting from Imperfect Tracking