This work proposes a training-free representation refinement that aligns frozen embeddings without updating either encoder, which preserves the spatial information of the Perception Encoder, converts its patch grid into a compact set of learned visual views, and aggregates them for each image with a block-structured, c...
Salini Yadav, Taveena Lotey, Mickael Coustaty et al.· 0 citations
Findings show that reliable post-hoc explanation requires domain-aware interpretable representations, and that segmentation should be treated as part of the explanation method rather than as neutral preprocessing.
Quentin Telnoff, Emanuela Boroş, Mickael Coustaty et al.· 0 citations
Multi-negative direct preference optimisation (MDPO), a reference-based pairwise objective that compares the correct entity with all valid rejected candidates associated with each mention, demonstrates that incorporating all within-instance negative candidates is a simple and effective improvement for LLM-based histori...
Tien N. Nguyen, Emanuela Boros, Ahmed Hamdi et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.