3 papers
cs.LG2026
Removing Information Content Does Not Certify Tamper Resistance in Open-Weight Models
Domenic Rosati, Alessa Carbo, Ali Dadsetan +5
Does removing harmful information make open-weight models resistant to fine-tuning attacks? We show that mutual information at release alone cannot universally certify slow recover…
cs.AI2026
Beyond a Single Reference: Training and Evaluation with Paraphrases in Sign Language Translation
Václav Javorek, Tomáš Železný, Alessa Carbo +2
Most Sign Language Translation (SLT) corpora pair each signed utterance with a single written-language reference, despite the highly non-isomorphic relationship between sign and sp…
cs.CV2025
Improving Handshape Representations for Sign Language Processing: A Graph Neural Network Approach
Alessa Carbo, Eric Nalisnick
Handshapes serve a fundamental phonological role in signed languages, with American Sign Language employing approximately 50 distinct shapes. However,computational approaches rarel…