|
Javad Rajabi
I am a CS PhD Student at University of Toronto (UofT), and a Faculty Affiliate Researcher at Vector Institute, co-supervised by David B. Lindell and Babak Taati. Currently, I am a research intern at Samsung AI Center Toronto.
Currently, my research focuses on inference-time guidance and scaling for diffusion and flow-matching models, using targeted search, sampling, and steering signals to improve generation quality and control specific attributes. I am exploring novel guidance signals (e.g., intrinsic confidence, perturbation-based methods, reward models, textual feedback, etc.) that can score partial states or full trajectories.
Email
CV
Google Scholar
Twitter
GitHub
LinkedIn
|
