15 papers
InsertFuse: A Unified Framework for Multi-Category Reference-Guided Image Insertion
Guangzhao Li, Qingyan Wei, Huayu Zheng +7
We present InsertFuse, a unified framework for multi-category reference-guided image insertion. Its key idea is to decouple category-specific expertise learning from cross-category…
STEP-OPD: Rethinking Output Targets and Internal Dynamics in On-Policy Distillation for Diffusion Models
Qingyan Wei, Guangzhao Li, Xiaobing Tu +5
On-policy distillation (OPD) has become an effective approach for consolidating multiple task-specialized image generation models into a single student. However, existing OPD metho…
Rarity-Aware Discrete Diffusion with Spatially Consistent Decoding for Photo-Realistic Image Super-Resolution
Ao Li, Yapeng Du, Yi Xin +5
Continuous diffusion models have become the dominant paradigm for photo-realistic image Super-Resolution (SR), but they typically formulate reconstruction as continuous signal-leve…
A First-Principles Derivation of LLM Policy Optimization: From Expected Reward to GRPO and Its Structural Extensions
Jianghan Shen, Siqi Luo, Yue Li +9
Policy gradient algorithms for language models optimize the same objective , which has exactly two factors: the trajectory probability…
Sketch Then Paint: Hierarchical Reinforcement Learning for Diffusion Multi-Modal Large Language Models
Siqi Luo, Jianghan Shen, Yi Xin +9
Diffusion Multi-Modal Large Language Models (dMLLMs) are powerful for image generation, but optimizing them through reinforcement learning (RL) remains a major challenge. One prima…
Prism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models
Jinbin Bai, Yixuan Li, Yuchen Zhu +8
Inference-time compute has re-emerged as a practical way to improve LLM reasoning. Most test-time scaling (TTS) algorithms rely on autoregressive decoding, which is ill-suited to d…