2 papers
cs.CL2024
Chart-based Reasoning: Transferring Capabilities from LLMs to VLMs
Victor Carbune, Hassan Mansoor, Fangyu Liu +4
Vision-language models (VLMs) are achieving increasingly strong performance on multimodal tasks. However, reasoning capabilities remain limited particularly for smaller VLMs, while…
eess.IV2022
Lippmann Photography: A Signal Processing Perspective
Gilles Baechler, Michalina Pacholska, Arnaud Latty +2
Lippmann (or interferential) photography is the first and only analog photography method that can capture the full color spectrum of a scene in a single take. This technique, inven…