Xiuyu Li
@sheriyuo
Researcher @StepFun_ai | Working on long-horizon tasks | Prev @RUC1937 | Opinions are my own
Joined February 2026
1.7K Following 12.4K Followers
Qwen-Image-2.0-RL Technical Report
Paper:
They fine-tune VLMs to score pointwise with CoT, so the reward judges alignment against an explanation and is harder to game.
OPD then closes the train-inference gap on the diffusion backbone.
Show more
