2 papers
cs.CV2026
CARD: Diagnosing Belief to Action Routing Failures in Vision Language Models
Souptik Kumar Majumdar, Fabian Kögel, Andreas Bulling
Linear probes and activation steering have uncovered that vision-language models (VLMs) internally represent mental states such as agents' beliefs, knowledge, and intentions. Howev…
cs.CV2024
Attention Is All You Need For Mixture-of-Depths Routing
Advait Gadhikar, Souptik Kumar Majumdar, Niclas Popp +3
Advancements in deep learning are driven by training models with increasingly larger numbers of parameters, which in turn heightens the computational demands. To address this issue…