Good Papers

Showing papers from Technical University of Darmstadt Show all papers

57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026Technical University of DarmstadTU DarmstadtBlack Forest LabsSparse autoencoders

Do Sparse Autoencoders Learn Meaningful Concept Hierarchies?

Nils Grandien, David Steinmann, Felix Friedrich, Kristian Kersting

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 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 2026Computer Science Department, TU TU DarmstadtTechnical University of DarmstadRobert Bosch GmbHExplainable AI

xWhy: Causal Learning from Explanations

Nicholas Tagliapietra, Florian Peter Busch, Moritz Willig, Matej Zečević and 3 more

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
88%Must read
?Must readVote to see the score
NeurIPS 2026ELLIS Institute TübingenTechnical University of DarmstadELLIS Institute & MPI IntellAI oversight & deception

Models That Know How Evaluations Are Designed Score Safer

Models with evaluation meta-knowledge about benchmark structures score safer via implicit behavioral shifts, confounding safety assessments independently of explicit awareness.

Katharina Deckenbach, Haritz Puerto, Jonas Geiping, Sahar Abdelnabi

Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 PM, Paris Poster Hall · Published 2026 · ▲ 6 on Hugging Face · Code ★ 3

– ReadersNo votes yet
15/20 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: 15 of 20 reviewers recommend it
lenient 5/5
medium 9/10
strict 1/5
86%Must read
?Must readVote to see the score
NeurIPS 2026Technische Universität DarmstadtTechnical University of DarmstadCornellTechnical University DarmstadtTU DarmstadtAgent benchmarks & environments

Playing ZendoWorld: Challenging AI Agents on Active Visual Concept Induction

ZendoWorld evaluates AI agents on active visual rule induction and finds high prediction accuracy does not imply rule recovery, with VLM agents proposing near-uninformative experiments.

Sophia Koehler, Antonia Wüst, Inga Ibs, Top Piriyakulkij and 4 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
14/20 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: 14 of 20 reviewers recommend it
lenient 5/5
medium 7/10
strict 2/5