Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
Difference Feedback: Generating Multimodal Process-Level Supervision for VLM Reinforcement Learning
Feiding, Yongkang Zhang, Yuhao Liao +10
Vision--language models (VLMs) are increasingly aligned via Group Relative Policy Optimization (GRPO)-style training. However, relying solely on terminal outcome rewards yields spa…
cs.CV2025
Rhetorical Text-to-Image Generation via Two-layer Diffusion Policy Optimization
Yuxi Zhang, Yueting Li, Xinyu Du +1
Generating images from rhetorical languages remains a critical challenge for text-to-image models. Even state-of-the-art (SOTA) multimodal large language models (MLLM) fail to gene…