Research map / Vision-language and multimodal / CLIP and zero-shot
JoPPO: Hierarchical Photography Assessment via Contrastive Joint Conditional Probabilistic Reinforcement Learning
Yifan Yang, Juntuo Wang, Yuming Qiao, Xudong Zhang, Chunyang Yu, Yan Li, Xiao Lin, Liang Luo, Dan Meng
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add compositional SFT stage (ablation) | JoPPO (Qwen2.5-VL-7B) · PICD | accuracy: 0.444 -> 0.720 | Improved |
| add compositional SFT stage (ablation) | JoPPO (Qwen2.5-VL-7B) · MMPerspective | accuracy: 0.547 -> 0.624 | Improved |
| add compositional SFT stage (ablation) | JoPPO (Qwen2.5-VL-7B) · CADB | SRCC: 0.596 -> 0.629 | Improved |
| add compositional SFT stage (ablation) | JoPPO (Qwen2.5-VL-7B) · PARA | SRCC: 0.761 -> 0.789 | Improved |
| use JoPPO joint conditional probability RL instead of GRPO (ablation) | JoPPO (Qwen2.5-VL-7B) · PICD | accuracy: 0.674 -> 0.720 | Improved |
| use JoPPO instead of GRPO (ablation) | JoPPO (Qwen2.5-VL-7B) · MMPerspective | accuracy: 0.621 -> 0.624 | Improved |
| use JoPPO instead of GRPO (ablation) | JoPPO (Qwen2.5-VL-7B) · CADB | SRCC: 0.566 -> 0.629 | Improved |
| use JoPPO instead of GRPO (ablation) | JoPPO (Qwen2.5-VL-7B) · PARA | SRCC: 0.723 -> 0.789 | Improved |
| use JoPPO instead of GRPO (ablation) | JoPPO (Qwen2.5-VL-7B) · PARA attribute-to-overall | Overall SRCC: 0.723 -> 0.789 | Improved |
| use JoPPO model vs GPT-4o | JoPPO (Qwen2.5-VL-7B) · PARA (zero-shot) | SRCC: 0.678 -> 0.764 | Improved |
| use JoPPO model vs GPT-4o | JoPPO (Qwen2.5-VL-7B) · PICD | accuracy: 0.393 -> 0.720 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- Artimuse — ArtiMuse: Fine-Grained Image Aesthetics Assessment with Joint Scoring and Expert-Level Understanding (CVPR 2026) · better on 4 of 4 shared results
- Q-Insight — Q-Insight: Understanding Image Quality via Visual Reinforcement Learning (NeurIPS 2025) · better on 4 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Reasoning as Representation: Rethinking Visual Reinforcement Learning in Image Quality Assessment (ICLR 2026 · similarity 0.86)
- VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank (NeurIPS 2025 · similarity 0.86)
- Unlocking the Essence of Beauty: Advanced Aesthetic Reasoning with Relative-Absolute Policy Optimization (ICLR 2026 · similarity 0.86)
- Sketch Then Paint: Hierarchical Reinforcement Learning for Diffusion Multi-Modal Large Language Models (NeurIPS 2026 · similarity 0.86)
- Probabilistic Prompt Adaptation for Unified Image Aesthetics and Quality Assessment (CVPR 2026 · similarity 0.86)
- Focusing Where Vision Matters: Selective Training for Large Vision Language Models via Visual Information Gain (ICML 2026 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
