Good Papers

Showing papers from IWR, Heidelberg University Show all papers

83%Must read
?Must readVote to see the score
NeurIPS 2026Interdisciplinary Center for SciU TübingenIWR, HeidelbergHeidelberg University, Ruprecht-Time series forecasting

The Dynamic-Probabilistic Consistency Gap in Chaotic Surrogate Modeling

Finite-horizon probabilistic training creates a consistency gap that decouples uncertainty from local dynamics in chaotic surrogates; a Kalman-aware framework evaluating local innovations while transporting covariance through learned Jacobians closes it.

Andre Herz, Matthijs Pals, Daniel Durstewitz, Georgia Koppe

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
13/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 13 of 20 reviewers recommend it
lenient 2/5
medium 10/10
strict 1/5
74%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026SpotlightCentral Institute of Mental HealRuprecht-Karls-Universität HeideIWR, HeidelbergTime series forecasting

Parallel-in-Time Training of Recurrent Neural Networks for Dynamical Systems Reconstruction

DEER with generalized teacher forcing trains recurrent networks in parallel time to learn nonlinear dynamics on long sequences, outperforming linear state-space models for systems with long time scales.

Florian Hess, Florian Götz, Daniel Durstewitz

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 1 on Hugging Face

– ReadersNo votes yet
9/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 9 of 20 reviewers recommend it
lenient 3/5
medium 6/10
strict 0/5
80%Must read
?Must readVote to see the score
NeurIPS 2026Ruprecht-Karls-Universität HeideCentral Institute of Mental HealCentral Institute Of Mental HealIWR, HeidelbergTime series forecasting

Topological Out-of-Domain Generalization in Dynamical Systems Reconstruction

This paper fixes structural mismatches in dynamical system reconstruction via feature splitting to enable zero-shot out-of-domain forecasting across tipping points with derived extrapolation bounds.

Georg Trede, Charlotte Doll, Elias Daniel Weber, Daniel Durstewitz

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 12 of 20 reviewers recommend it
lenient 4/5
medium 7/10
strict 1/5
80%Must read
?Must readVote to see the score
NeurIPS 2026Ruprecht-Karls-Universität HeideHeidelbergIWR, HeidelbergTime series foundation models

A Minimal Interpretable Architecture for Zero-Shot Reconstruction of Dynamical Systems

DynaBase, a two-parameter model blending latent states with nearest in-context neighbors, achieves competitive zero-shot dynamical reconstruction with orders-of-magnitude fewer parameters.

Christoph Jürgen Hemmer, Florian Plaswig, Daniel Durstewitz

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 12 of 20 reviewers recommend it
lenient 4/5
medium 7/10
strict 1/5