The L3S regularly honours the authors of the best publications of the quarter, which were presented at renowned conferences (A*) or published in high-ranking journals (Q1).

2025/Q2
Aligning Visual Contrastive Learning Models via Preference Optimization
Enhancing Online Climate Discourse: A Two-Stage Framework for Climate Content Categorization and Moderation
FedFlow: A Personalized Federated Learning Framework for Passenger Flow Prediction
Interpretable zero-shot stance detection with proactive content intervention
SimE: A Knowledge Graph Embedding Model to Encode Self-Similar Structures Through Algebraic and Geometric Transformations
UncertainSAM: Fast and Efficient Uncertainty Quantification of the Segment Anything Model