3 papers
cs.CV2026
Label-efficient underwater species classification with logistic regression on frozen foundation model embeddings
Thomas Manuel Rost
Automated species classification from underwater imagery is bottlenecked by the cost of expert annotation, and supervised models trained on one dataset rarely transfer to new condi…
cs.CV2026
Inference-Path Optimization via Circuit Duplication in Frozen Visual Transformers for Marine Species Classification
Thomas Manuel Rost
Automated underwater species classification is constrained by annotation cost and environmental variation that limits the transferability of fully supervised models. Recent work ha…
cs.CL2025
Stated Preference for Interaction and Continued Engagement (SPICE): Evaluating an LLM's Willingness to Re-engage in Conversation
Thomas Manuel Rost, Martina Figlia, Bernd Wallraff
We introduce and evaluate Stated Preference for Interaction and Continued Engagement (SPICE), a simple diagnostic signal elicited by asking a Large Language Model a YES or NO quest…