Good Papers

Showing papers from TU Munich Show all papers

45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026The University of QueenslandELLIS Institute Finland | AaltoTU MunichAaltoDiffusion models

Directional Noise Conditioning for Diffusion Models

Mahdi Shafiei, Azade Farshad, Nassir Navab, Yousef Yeganeh

Sydney Poster Session 3, Wed, Dec 9, 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 2026OralMITMassachusetts Institute of TechnTU MunichSelf-supervised vision

Shaping Useful Noise: Energy Distributions Predict Visual Pretraining Quality

Ching Lam Choi, Antonio Torralba, Phillip Isola, Stefanie Jegelka

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 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 2026LMU MunichTU MunichMarburguniversityPhysics-informed ML & PDEs

Conformal Prediction for Time-Dependent PDEs

Joshua Stiller, Annika Schneider, Eyke Hüllermeier

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 2026Technical University of MunichTU MunichDeep learning theory

Spectral Re-Basin for Linear Mode Connectivity

Ya-Wei Eileen Lin, Thomas Dagès, Daniel Herbst, Daniel Cremers and 1 more

Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 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
78%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026TU MunichU TwenteHEC ParisDeep RL

Breaking the Grid: Distance-Guided Reinforcement Learning in Large Discrete Action Spaces

DGRL enables efficient reinforcement learning in discrete action spaces up to 10^20 via distance-guided exploration and regression-based updates, improving performance by up to 66%.

Heiko Hoppe, Fabian Akkerman, Wouter van Heeswijk, Maximilian Schiffer

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · 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 5/5
medium 5/10
strict 1/5
80%Must read
?Must readVote to see the score
NeurIPS 2026Technical University of MunichTechnical University of MunichMercedes-BenzTU MunichGoogle, TUMSegmentation

Prompting Diffusion Models for Zero-Shot Instance Segmentation

Prompt2Seg conditions frozen diffusion segmentation models on spatial prompts for zero-shot interactive instance segmentation across diverse visual domains.

İrem Z Alagöz, Nils Morbitzer, Andrea Ramazzina, Nassir Navab and 2 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 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 5/5
medium 7/10
strict 0/5
83%Must read
?Must readVote to see the score
NeurIPS 2026TU MunichTechnische Universität MünchenStanfordMechanistic interpretability

What Cohort INRs Encode, and Where to Freeze Them

Freezing cohort INR layers at highest stable-rank depth improves fitting, with sparse autoencoders revealing SIREN learns localized atoms and FFMLP learns image-spanning memorized contours.

Vasiliki Sideri-Lampretsa, Sophie Starck, Robbie Holland, Julian McGinnis and 1 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 3/5
medium 7/10
strict 3/5
78%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026Technical University of MunichImperial College LondonTU MunichPose & motion

COMPOSE: Hypergraph Cover Optimization for Multi-view 3D Human Pose Estimation

COMPOSE recasts multi-view 3D pose estimation as hypergraph exact-cover optimization, improving training-free average precision by up to 31 points over prior optimization methods.

Tony Danjun Wang, Tolga Birdal, Nassir Navab, Lennart Bastian

Paris Poster Session 3, Thu, Dec 10, 12:30 PM–2:30 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 5/5
medium 5/10
strict 1/5