Deepak Ramachandran

A new method enhances AI learning using offline preference data and human feedback.

2025-07-29T14:03:00+00:00 ― 7 min read

A novel algorithm for optimizing decision-making under constraints in episodic settings.

2025-07-29T13:55:06+00:00 ― 5 min read

Investigating fine-grained feedback for text-to-image models and its practical implications.

2025-07-24T23:34:54+00:00 ― 6 min read

Discover the latest developments in text-to-image models and their impact.

2025-06-28T15:42:48+00:00 ― 7 min read