Good Papers

Showing papers from Linköping University Show all papers

57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026LinköpingU GroningenSoutheastMohamed bin Zayed University of LLM reasoning & chain of thought

Geometric Instability of Hidden-State Trajectories Predicts Reasoning Failures in Large Language Models

Hoda Fakharzadehjahromy, Andreas C Bueff, Fredrik Heintz, Mattias Tiger and 3 more

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

– ReadersNo votes yet
1/20 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: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026LinköpingVideo generation

Learning to Deaggregate: Large-scale Trajectory Generation with Spatial Priors

David Bergström, Mattias Tiger, Fredrik Heintz

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

– ReadersNo votes yet
0/20 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: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026LinköpingUppsalaFlow matching

ESS-Flow: training-free guidance as Bayesian inference in source space

Adhithyan Kalaivanan, Zheng Zhao, Jens Sjölund, Fredrik Lindsten

Paris Poster Session 1, Wed, Dec 9, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
0/20 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: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
76%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026RWTH AachenRheinisch Westfälische TechnischLinköpingLLM agents & planning

Efficient Lookahead Encoding and Abstracted Width for Learning General Policies in Classical Planning

Holistic relational encoding and abstracted width enable GNN policies to learn general classical planning strategies efficiently, surpassing LAMA on IPC 2023 benchmarks.

Michael Aichmüller, Simon Ståhlberg, Martin Funkquist, Hector Geffner

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

– ReadersNo votes yet
10/20 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: 10 of 20 reviewers recommend it
lenient 2/5
medium 7/10
strict 1/5
83%Must read
?Must readVote to see the score
NeurIPS 2026U HelsinkiETH ZurichLinköpingWeather & climate

Njord: A Probabilistic Graph Neural Network for Ensemble Ocean Forecasting

Njord is a probabilistic graph neural network that produces efficient ensemble ocean forecasts via single-pass sampling, achieving lowest average upper-ocean errors globally and in the Baltic Sea.

Daniel Holmberg, Joel Oskarsson, Erik Wikingsson, Fredrik Lindsten and 1 more

Sydney Poster Session 5, Thu, Dec 10, 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 5/5
medium 6/10
strict 2/5