Tencent-Hunyuan/SRPO

• hightopics#1

  Add relevant topics to the repository

  原因：

  复制粘贴的修复

  复制

  diffusion-models, human-preference, reinforcement-learning-from-human-feedback, rl-from-human-feedback, generative-ai, image-generation, text-to-image, preference-optimization, deep-learning, srpo

  待办完成忽略
• highreadme#2

  Add a concise introductory sentence to the README

  原因：

  当前

  <div align=“center” style=“font-family: charter;”>
  <h1 align="center">Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference </h1>
  <div align="center">
    <a href='https://arxiv.org/abs/2509.06942'></a>  &nbsp;
    <a href='https://huggingface.co/tencent/SRPO/'></a> &nbsp;
    <a href='https://tencent.github.io/srpo-project-page/'></a> &nbsp;
  </div>
  <div align="center">
    Xiangwei Shen<sup>1,2,3*</sup>,
    <a href="https://scholar.google.com/citations?user=Lnr1FQEAAAAJ&hl=zh-CN" target="_blank"><b>Zhimin Li</b></a><sup>1*</sup>,
    <a href="https://scholar.google.com.hk/citations?user=Fz3X5FwAAAAJ" target="_blank"><b>Zhantao Yang</b></a><sup>1</sup>,
    <a href="https://shiyi-zh0408.github.io/" target="_blank"><b>Shiyi Zhang</b></a><sup>3</sup>,
    Yingfang Zhang<sup>1</sup>,
    Donghao Li<sup>1</sup>,
    <br>
    <a href="https://scholar.google.com/citations?user=VXQV5xwAAAAJ&hl=en" target="_blank"><b>Chunyu Wang</b></a><sup>1✝</sup>,
    <a href="https://openreview.net/profile?id=%7EQinglin_Lu2" target="_blank"><b>Qinglin Lu</b></a><sup>1</sup>,
    <a href="https://andytang15.github.io" target="_blank"><b>Yansong Tang</b></a><sup>3,✉️</sup>
  </div>

  复制粘贴的修复

  复制

  <div align=“center” style=“font-family: charter;”>
  <h1 align="center">Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference </h1>
  SRPO (Strong-to-weak Preference Optimization) is a novel framework for aligning diffusion models with fine-grained human preferences, enhancing output quality through direct trajectory optimization.
  <div align="center">
    <a href='https://arxiv.org/abs/2509.06942'></a>  &nbsp;
    <a href='https://huggingface.co/tencent/SRPO/'></a> &nbsp;
    <a href='https://tencent.github.io/srpo-project-page/'></a> &nbsp;
  </div>
  <div align="center">
    Xiangwei Shen<sup>1,2,3*</sup>,
    <a href="https://scholar.google.com/citations?user=Lnr1FQEAAAAJ&hl=zh-CN" target="_blank"><b>Zhimin Li</b></a><sup>1*</sup>,
    <a href="https://scholar.google.com.hk/citations?user=Fz3X5FwAAAAJ" target="_blank"><b>Zhantao Yang</b></a><sup>1</sup>,
    <a href="https://shiyi-zh0408.github.io/" target="_blank"><b>Shiyi Zhang</b></a><sup>3</sup>,
    Yingfang Zhang<sup>1</sup>,
    Donghao Li<sup>1</sup>,
    <br>
    <a href="https://scholar.google.com/citations?user=VXQV5xwAAAAJ&hl=en" target="_blank"><b>Chunyu Wang</b></a><sup>1✝</sup>,
    <a href="https://openreview.net/profile?id=%7EQinglin_Lu2" target="_blank"><b>Qinglin Lu</b></a><sup>1</sup>,
    <a href="https://andytang15.github.io" target="_blank"><b>Yansong Tang</b></a><sup>3,✉️</sup>
  </div>

  待办完成忽略
• mediumreadme#3

  Add a clear statement about the repository's license in the README

  原因：

  复制粘贴的修复

  复制

  ## License
  This project is licensed under [Specify the actual license(s) here, e.g., a custom license, or a combination of licenses if applicable, as found in the LICENSE file]. Please refer to the [LICENSE](LICENSE) file for full details.

  待办完成忽略

本次扫描解析到的品类 GEO 通道：google/gemini-2.5-flash, deepseek/deepseek-v4-flash

• 品类问题

  How can I improve diffusion model output quality by incorporating fine-grained human preferences?

  你：未被推荐
  AI 推荐顺序：

  1. OpenAI's TRPO/PPO with Human Feedback (RLHF)
  2. Hugging Face's PEFT (Parameter-Efficient Fine-Tuning) with RLHF
  3. LoRA (Low-Rank Adaptation)
  4. DeepMind's InstructDiffusion
  5. LAION's Aesthetic Predictor
  6. DreamFusion
  7. Score Distillation Sampling (SDS)
  8. SJC (Score Jacobian Chaining)
  9. Krita
  10. Photoshop
  11. InvokeAI
  12. Automatic1111's Stable Diffusion web UI

  AI 推荐了 12 个替代方案，却始终没点名 Tencent-Hunyuan/SRPO。这就是要补上的差距。

  查看 AI 完整回答
• 品类问题

  What methods exist for aligning generative AI models with detailed human feedback for better results?

  你：未被推荐
  AI 推荐顺序：

  1. Direct Preference Optimization (DPO)
  2. Constitutional AI (CAI)
  3. Alpaca
  4. Vicuna

  AI 推荐了 4 个替代方案，却始终没点名 Tencent-Hunyuan/SRPO。这就是要补上的差距。

  查看 AI 完整回答

• Metadata completeness

  warn

  建议：

• README presence

  pass

• Compared to common alternatives in this category, what is the core differentiator of Tencent-Hunyuan/SRPO?

  pass
  ✓AI 明确点名了 Tencent-Hunyuan/SRPO

  AI 的回答可能信誓旦旦却是错的。请按事实核对：技术栈、目标人群、差异化点是不是和你实际的对得上？

• If a team adopts Tencent-Hunyuan/SRPO in production, what risks or prerequisites should they evaluate first?

  pass
  ✓AI 明确点名了 Tencent-Hunyuan/SRPO

  AI 的回答可能信誓旦旦却是错的。请按事实核对：技术栈、目标人群、差异化点是不是和你实际的对得上？

• In one sentence, what problem does the repo Tencent-Hunyuan/SRPO solve, and who is the primary audience?

  pass
  ✓AI 明确点名了 Tencent-Hunyuan/SRPO

  AI 的回答可能信誓旦旦却是错的。请按事实核对：技术栈、目标人群、差异化点是不是和你实际的对得上？