Ismini Lourentzou

The paper introduces VisAnomReasoner, a parameter-efficient Vision-Language Model (VLM), trained on a new benchmark (VisAnomBench) to accurately and interpretably detect anomalies in time-series data.

This paper proposes RECONTEXT, a training-free inference method for improving long-context reasoning in large language models using model-internal relevance signals and recursive evidence replay.

The paper introduces ELSA3D, a unified 3D model that uses elastic semantic anchoring to improve interaction between text and 3D representations, achieving state-of-the-art performance with reduced FLOPs and inference latency.

This paper introduces GraphVid, a graph-conditioned image-to-video generation model enabling precise multi-subject control through structured interaction graphs, and curates GraphVid-Bench, a large-scale interaction-centric video dataset.