Efficient text-to-image generation requires both reinforcement-learning (RL)-based reward alignment and few-step distillation, yet these procedures are typically performed sequentially, increasing training cost and risking the loss of reward gains during compression. We instead take an RL-native perspective: diffusion RL already generates reward-scored finite-step trajectories, whose intermediate states provide a natural source of distillation supervision rather than a disposable byproduct of sampling.
The paper introduces Reward-Aware Trajectory Shaping (RATS), a lightweight framework that aligns teacher and student latent trajectories at key denoising stages while adaptively regulating teacher guidance through a reward-aware gate. By allowing the student to optimize toward reward-preferred generation quality, RATS can surpass the teacher rather than merely imitate it. Experiments show that RATS improves the efficiency–quality trade-off in few-step visual generation, narrowing the gap between few-step students and stronger multi-step generators without extra test-time cost.
By Rui Li, Bingyu Li, Yuanzhi Liang, Haibin Huang, Chi Zhang, XueLong Li
arXiv:2606. 27608v1 Announce Type: cross Abstract: We present Qwen-Image-2.
By Yixian Xu, Kaiyuan Gao, Yuxiang Chen, Yilei Chen, Zecheng Tang, Zihao Liu, Zikai Zhou, Deqing Li, Hao Meng, Kuan Cao, Jiahao Li, Jie Zhang, Liang Peng, Lihan Jiang, Ningyuan Tang, Shengming Yin, Tianhe Wu, Xiaoyue Chen, Yan Shu, Yanran Zhang, Yi Wang, Yu Wu, Yujia Wu, Zekai Zhang, Zhendong Wang, Xiao Xu, Kun Yan, Chenfei Wu
DyMD introduces a Distribution Matching Distillation framework that adapts teacher supervision and critic fitting to preserve interaction dynamics in few-step video generation. By employing temporal affinity–conditioned re‑noise sampling and dynamics‑guided fake‑score tracking, DyMD balances motion recovery with visual quality. The method distills a 14B teacher into a 1.3B student that achieves significant gains on embodied‑video benchmarks and downstream action planning tasks.
By Haojun Xu, Jie Huang, Xin Lu, Mingchen Zhong, Zihao Fan, Linjiang Huang, Si Liu
arXiv:2606. 17979v1 Announce Type: new Abstract: Existing RL post-training methods for text-to-image generation usually convert the final-image reward into a single scalar advantage and apply it with the same strength to the entire generative trajectory.
By Jinjie Shen, Wei Deng, Xian Hu, Daiguo Zhou, Jian Luan
arXiv:2602. 07345v2 Announce Type: replace-cross Abstract: Distribution Matching Distillation (DMD) is a powerful acceleration paradigm, yet its stability is often compromised in Forbidden Zone, regions where the real teacher provides unreliable guidance while the fake teacher exerts insufficient repulsive force.
By Lichen Bai, Zikai Zhou, Shitong Shao, Wenliang Zhong, Shuo Yang, Shuo Chen, Bojun Chen, Zeke Xie
arXiv:2604. 00626v4 Announce Type: replace Abstract: As Large Language Models continue to grow in both capability and cost, transferring frontier capabilities into smaller, deployable students has become an important engineering problem, and knowledge distillation remains a common technique for this transfer.
By Mingyang Song, Mao Zheng
arXiv:2605. 06094v5 Announce Type: replace-cross Abstract: Training VideoLLMs for complex reasoning remains challenging due to sparse sequence level rewards and the lack of fine grained credit assignment over long, temporally grounded reasoning trajectories.
By Hao Lin, Kunyang Lv, Xu Jiang, Jingqi Tian, Zhongjing Du, Jiayu Ding, Qiaoman Zhang, Hongbo Jin
arXiv:2605. 30116v2 Announce Type: replace-cross Abstract: Distribution Matching Distillation (DMD) is a widely used paradigm for accelerating inference in few-step video diffusion models.
By Zhuguanyu Wu, Ruihao Gong, Yang Yong, Yushi Huang, Xiangyu Fan, Lei Yang, Dahua Lin, Xianglong Liu
arXiv:2607. 17247v1 Announce Type: cross Abstract: Large language model (LLM) post-training is essential for improving reasoning, adaptation, and alignment.
By Chen Wang, Zhaochun Li, Jionghao Bai, Yining Zhang, Hexuan Deng, Ge Lan, Yue Wang
arXiv:2604. 28123v3 Announce Type: replace-cross Abstract: The standard post-training recipe for large multimodal models (LMMs) applies supervised fine-tuning (SFT) on curated demonstrations followed by reinforcement learning with verifiable rewards (RLVR).
By Sudong Wang, Weiquan Huang, Xiaomin Yu, Zuhao Yang, Hehai Lin, Keming Wu, Chaojun Xiao, Chen Chen, Wenxuan Wang, Beier Zhu, Yunjian Zhang, Chengwei Qin
arXiv:2607. 18955v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning capabilities of large language models on tasks such as mathematical reasoning and code generation.
By Qiye Cai, Yichuan Ma, Linyang Li, Peiji Li, Yongkang Chen, Qipeng Guo, Yicheng Zou, Tao Gui, Xiaocheng Feng, Bing Qin