Good Papers

Showing papers from CentraleSupelec Show all papers

86%Must read
?Must readVote to see the score
NeurIPS 2026Université Paris-SaclayCentraleSupelecLaboratoire de recherche en infoRepresentation & contrastive learning

Drive vs. Decay: On the Training Dynamics of Joint-Embedding Predictive Architectures

Linearizing JEPA gradient flow reveals competing drive and decay effects that unify collapse-avoidance heuristics and predict a stability phase boundary, leading to ResidualPred, which improves rank and accuracy.

José Lucas De Melo Costa, Seong Woo Ahn, Fabrice Popineau, Arpad Rimmel and 1 more

Sydney Poster Session 6, Thu, Dec 10, 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 2/5
medium 10/10
strict 2/5
78%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026ETH ZürichETS MontrealCentraleSupelecCentraleSupélecUncertainty & calibration

Class Adaptive Conformal Training

Class Adaptive Conformal Training adaptively shapes class-conditional prediction sets via augmented Lagrangian optimization without distributional assumptions, yielding smaller sets with valid coverage.

Badr-Eddine Marani, Julio Silva-Rodríguez, Ismail Ayed, Maria Vakalopoulou and 2 more

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 4/5
medium 7/10
strict 0/5
76%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026HarokopioU Athens & Archimedes AI, AtCentraleSupelecHarokopio University of AthensObject detection

GATE-AD: Graph Attention Network Encoding for Few-Shot Industrial Visual Anomaly Detection

GATE-AD employs graph attention networks with masked reconstruction to detect industrial anomalies from few normal samples, achieving state-of-the-art accuracy with faster inference across benchmarks.

Aggelos Psiris, Yannis Panagakis, Maria Vakalopoulou, Georgios Th. Papadopoulos

Sydney Poster Session 1, Tue, Dec 8, 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 5/5
medium 5/10
strict 0/5