My journey from blurry pixel-diffusion to a multi-objective Latent Model that learns biological plausibility through protein-to-protein translation.
Read more →Building the first surgical vision world model that enables action-controllable generation without expensive action labels.
Read more →Bridging the gap between basic MDPs and the math behind PPO/A3C. Why the 'Log-Derivative Trick' is the engine of modern RL.
Read more →Why standard Monte Carlo Tree Search fails in card games, and how Information Set MCTS solves the hidden information problem.
Read more →