5 papers
Future Querying: Can LLMs Serve as Implicit Medical World Models?
Siri Willems, James Butterworth, Lore Goetschalckx +4
Traditional clinical prediction models rely on task-specific pipelines and curated, structured data, which scale poorly and underutilize unstructured text. To address this, we intr…
Addressing Detail Bottlenecks in Latent Diffusion for RGB-to-SWIR Image Translation
Kaili Wang, Martin Dimitrievski, Jose Maria Salvador +3
Latent diffusion models (LDMs) enable efficient image-to-image translation but discard fine spatial details during compression, degrading downstream perception tasks. We identify t…
Capability Interpretability: Human Interpretability of Vision Foundation Models
Julien Colin, Lore Goetschalckx, Nuria Oliver +1
How interpretable are the features of leading vision models? The question is increasingly pressing as these models move from research benchmarks into high-stakes deployments, yet e…
Choosing the right basis for interpretability: Psychophysical comparison between neuron-based and dictionary-based representations
Julien Colin, Lore Goetschalckx, Thomas Fel +3
Interpretability research often adopts a neuron-centric lens, treating individual neurons as the fundamental units of explanation. However, neuron-level explanations can be undermi…
Increasing the Diversity in RGB-to-Thermal Image Translation for Automotive Applications
Kaili Wang, Leonardo Ravaglia, Roberto Longo +5
Thermal imaging in Advanced Driver Assistance Systems (ADAS) improves road safety with superior perception in low-light and harsh weather conditions compared to traditional RGB cam…