2 papers
cs.LG2026
Multi-Axis Max@K Reinforcement Learning for Representative Diversity in Text-to-Image Generation
Ku Onoda, Paavo Parmas, Hiroki Furuta +4
Text-to-image (T2I) models can synthesize realistic, prompt-aligned images, yet samples generated for the same prompt often cover only a small subset of visually distinct modes. Th…
cs.LG2026
Does "Do Differentiable Simulators Give Better Policy Gradients?'' Give Better Policy Gradients?
Ku Onoda, Paavo Parmas, Manato Yaguchi +1
In policy gradient reinforcement learning, access to a differentiable model enables 1st-order gradient estimation that accelerates learning compared to relying solely on derivative…