13 Feb 2024
Latent Inversion with Timestep-aware Sampling for Training-free Non-rigid Editing
13 Feb 2024 · Preprint · arXiv · Computer Vision and Pattern Recognition
PhD Student · MBZUAI
I'm interested in semantic watermarking, which makes AI-generated text traceable by its meaning so the signal survives paraphrasing, and in scalable oversight, which asks how weaker supervisors can reliably evaluate and steer models stronger than themselves.
13 Feb 2024 · Preprint · arXiv · Computer Vision and Pattern Recognition
1 Jan 2024 · Preprint · SSRN Electronic Journal · Computer Vision and Pattern Recognition