AI Paper Atlas

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

CVPR 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Adapting VLMs for zero-shot classification

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 changedWhereMeasuredEffect
add compositional SFT stage (ablation)JoPPO (Qwen2.5-VL-7B) · PICDaccuracy: 0.444 -> 0.720Improved
add compositional SFT stage (ablation)JoPPO (Qwen2.5-VL-7B) · MMPerspectiveaccuracy: 0.547 -> 0.624Improved
add compositional SFT stage (ablation)JoPPO (Qwen2.5-VL-7B) · CADBSRCC: 0.596 -> 0.629Improved
add compositional SFT stage (ablation)JoPPO (Qwen2.5-VL-7B) · PARASRCC: 0.761 -> 0.789Improved
use JoPPO joint conditional probability RL instead of GRPO (ablation)JoPPO (Qwen2.5-VL-7B) · PICDaccuracy: 0.674 -> 0.720Improved
use JoPPO instead of GRPO (ablation)JoPPO (Qwen2.5-VL-7B) · MMPerspectiveaccuracy: 0.621 -> 0.624Improved
use JoPPO instead of GRPO (ablation)JoPPO (Qwen2.5-VL-7B) · CADBSRCC: 0.566 -> 0.629Improved
use JoPPO instead of GRPO (ablation)JoPPO (Qwen2.5-VL-7B) · PARASRCC: 0.723 -> 0.789Improved
use JoPPO instead of GRPO (ablation)JoPPO (Qwen2.5-VL-7B) · PARA attribute-to-overallOverall SRCC: 0.723 -> 0.789Improved
use JoPPO model vs GPT-4oJoPPO (Qwen2.5-VL-7B) · PARA (zero-shot)SRCC: 0.678 -> 0.764Improved
use JoPPO model vs GPT-4oJoPPO (Qwen2.5-VL-7B) · PICDaccuracy: 0.393 -> 0.720Improved

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy