Michael Toker

tokeron

NLP, Computer Vision, Text to Image, LLMs, VLMs, Interpretability, Explainability

updated a dataset 2 days ago

tokeron/slim-dataset

published a dataset 2 days ago

tokeron/slim-dataset

upvoted a paper 2 months ago

tokeron 's Spaces 2

Find and segment objects in images using SAM and Grounding DINO

Generate images from text prompts using intermediate layers of text encoders