1 citations · 1 across the 16 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Outcome-Confounded Local Supervision in On-Policy Distillation
Guoqing Ma
On-policy distillation (OPD) trains a student on its own trajectories while a teacher supplies dense token-level likelihoods at student-visited prefixes. These likelihoods are ofte…
cs.LG2026
DiT-Reward: Generative Representations for Text-to-Image Reward Modeling
Yuanming Yang, Guoqing Ma, Bo Wang +5
Can representations learned for image generation also support the evaluation of generated images? We study text-to-image reward prediction as a downstream task of generative repres…