Guided Trajectory Optimization with Sparse Scaling for Test-Time Diffusion
15h ago
Quick Take
RTS enhances diffusion models' generation performance through reward-guided trajectory scaling and sparse noise optimization.
Key Points
- Introduces a novel Reward-guided Trajectory Scaling method.
- Achieves 15.6% improvement in GenEval Score.
- Sets new SOTA with 60.4% enhancement in ImageReward score.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →arXiv cs.CV·Jinhao Jing, Zheng Ma, Jinwei Liang, Qiannian Zhao, Shawn Chen, Jing Yang, Por Lip Yee, Prayag Tiwari, Jingjing Bai, Benyou Wang, Lewei Lu, Zhan Su
3d ago FeaturedOriginal
GeoSym127K: Scalable Symbolically-verifiable Synthesis for Multimodal Geometric Reasoning
AI Summary
GeoSym127K introduces a scalable neuro-symbolic framework for enhanced geometric reasoning in multimodal models.