AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

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

Sakif Hossain, Julian Teusch, Jörg Müller

ECCV 2026 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Regression uncertainty quantification · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
fine-tune siMLPe (MeanFT)siMLPe · AMASS (H=25)MPJPE: 0.0919 -> 0.0588Improved
fine-tune siMLPe (MeanFT)siMLPe · AMASS (H=25)NLL: 12.76 -> 3.04Improved
add conformal quantile regression (Bridge-CQR)siMLPe-style predictor · AMASS (H=25)NLL: 12.76 -> 0.10Improved
use deep ensemble instead of single siMLPesiMLPe · Human3.6M (H=25)NLL: 12.84 -> 1.72Improved
use deep ensemble instead of single siMLPesiMLPe · 3DPW (H=25)NLL: 4.75 -> 0.79Improved
fine-tune siMLPe (MeanFT)siMLPe · LaFAN1-HF (H=25)NLL: 172.36 -> 99.80Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy