Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
SOAR: Self-Correction for Optimal Alignment and Refinement in Diffusion Models
You Qin, Linqing Wang, Hao Fei +4
The post-training pipeline for diffusion models currently has two stages: supervised fine-tuning (SFT) on curated data and reinforcement learning (RL) with reward models. A fundame…
cs.LG2026
Hierarchical SVG Tokenization: Learning Compact Visual Programs for Scalable Vector Graphics Modeling
Ximing Xing, Ziteng Xue, Zhenxi Li +8
Recent large language models have shifted SVG generation from differentiable rendering optimization to autoregressive program synthesis. However, existing approaches still rely on…