Alibaba open-sources PromptEcho for T2I rewards using frozen VLMs

阿里开源PromptEcho：用冻结多模态大模型为文生图训练提供高质量Reward

Alibaba open-sourced PromptEcho, which uses one frozen Qwen3-VL-32B forward pass to score T2I training rewards. It computes token-level cross-entropy for the original prompt under teacher forcing, then uses the negative value as a continuous reward. In 5,000 poster tests, text accuracy rose from 68% to 75%.

Why it matters: HKR-K is strong: the post gives a concrete reward mechanism and a 68%→75% text-accuracy result. HKR-H/R pass, but this is a training-side research release, not a flagship model or major product update.