Is there a way go finetune this and run it on my local academic pdf library (1-2k papers) ? I'd appreciate having a slightly crazy creative coach who can help me brainstorm new ideas!
Seems interesting! I think there is a unit missing when asking "when do you anticipate to publish next".. I'm assuming months but would be important to specify
Has anyone experiment with using VLM to detect "marks"? Thinking of pen/pencil based markings like underlines, circles,checkmarks.. Can these models do it?