News for hackers. Stuff that matters.

cvaman

Re:Fine-Tuning VLMs for Data Extraction on Friday October 04, 2024 @08:39AM (#41740777)
Is it possible to host multiple fine-tuned VLMs on a single machine? like multiple models sharing the GPU(s) for inference?
Re:Bridging Images and Text – A Survey of VLMs on Tuesday September 17, 2024 @03:08PM (#41571466)
Curious to know if VLMs be adapted/extended for video-based tasks (generating video summaries, question answering from video...) by understanding interframe context and temporal dynamics?