Good Papers

Showing papers from MPI for Intelligent Systems, Tübingen Show all papers

45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026California State University, NorU TrentoMPI for Intelligent Systems, TübRepresentation & contrastive learning

PVFormer: Proper Velocity Transformer for Stable and Scalable Hyperbolic Representation Learning

Xianglong Shi, Nicu Sebe, Bernhard Schölkopf, Ziheng Chen

Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 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
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026Vector InstituteU TorontoETH ZurichDepartment of Computer Science, Max Planck Institute for IntelliLLM evaluation & benchmarks

SuperSycophantic: Stress-Testing Frontier LLMs from Single- to Multi-Turn Sycophancy

Terry J Zhang, Oscar S Yasunaga, Wenyuan Jiang, Jessica Bo and 7 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 2026Microsoft Research / UIUCMPI for Intelligent Systems, TübMax Planck Institute for IntelliStanfordMITLLM evaluation & benchmarks

AI Construct Lexis: An Ontology of the Hidden Assumptions in AI Evaluation

Olawale Salaudeen, Florian E. Dorner, Tom Sühr, Sang Truong and 12 more

Sydney Poster Session 5, Thu, Dec 10, 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
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026McMasterVector InstituteDepartment of Computer Science, Carnegie MellonMPI for Intelligent Systems, TübAgent benchmarks & environments

AM-Bench: A Unified Taxonomy and Evaluation Suite for Agentic Misalignment

Eric Zhang, Terry J Zhang, Chijioke Ugwuanyi, Jerick Shi and 2 more

Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 PM, Paris Poster Hall · 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 2026Max Planck Institute for IntelliBrown University Meta FAIRMPI for Intelligent Systems, TübVision-language-action models

Perception for Action in Latent World Models

Petr Ivashkov, Randall Balestriero, Bernhard Schölkopf

Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 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
83%Must read
?Must readVote to see the score
NeurIPS 2026Max Planck Institute for Human DMilaMPI for Human DevelopmentMax-Planck InstituteMPI for Intelligent Systems, TübLLM reasoning & chain of thought

The Alien Space of Science: Sampling Coherent but Cognitively Unavailable Research Directions

A framework samples coherent but cognitively unavailable "alien" research directions by maximizing idea coherence while minimizing existing community availability, broadening explored vocabularies 3.5-7x over LLM baselines.

Alejandro H. Artiles, Martin Weiss, Levin Brinkmann, Iyad Rahwan and 5 more

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 5/5
medium 7/10
strict 1/5
78%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026Max Planck Institute For IntelliMPI for Intelligent Systems, TübMax-Planck InstituteRepresentation & contrastive learning

PENEX: AdaBoost-Inspired Neural Network Regularization

PENEX introduces a multi-class exponential loss optimized via first-order methods that increases margins and improves neural network generalization in low-data regimes.

Klaus-Rudolf Kladny, Bernhard Schölkopf, Michael Muehlebach

Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
11/20 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: 11 of 20 reviewers recommend it
lenient 4/5
medium 7/10
strict 0/5
89%Must read
?Must readVote to see the score
NeurIPS 2026EuroSafeAIETHZ - ETH ZurichMATS ResearchMPI for Intelligent Systems, TübVector InstituteAI oversight & deception

GT-HarmBench: Benchmarking AI Safety Risks Through the Lens of Game Theory

GT-HarmBench evaluates 15 frontier AI models on 1,535 multi-agent game-theoretic risk scenarios, finding 38% failure at socially beneficial actions and up to 18% improvement via interventions.

Pepijn Cobben, Xuanqiang A Huang, Thao Pham, Isabel Dahlgren and 3 more

Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
16/20 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: 16 of 20 reviewers recommend it
lenient 5/5
medium 9/10
strict 2/5
71%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026Max Planck Institute for IntelliUToronto & MPIMPI for Intelligent Systems, TübLLM evaluation & benchmarks

Causality can systematically address the monsters under the bench(marks)

Causality systematically addresses benchmark biases and artifacts by making assumptions explicit to model phenomena, formulate hypotheses, and clarify method strengths through common causal topologies.

Felix Leeb, Zhijing Jin, Bernhard Schölkopf

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

– ReadersNo votes yet
7/20 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: 7 of 20 reviewers recommend it
lenient 5/5
medium 2/10
strict 0/5