3 papers
cs.CV2026
Oracle Noise: Faster Semantic Spherical Alignment for Interpretable Latent Optimization
Haosen Li, Wenshuo Chen, Lei Wang +3
Text-to-image diffusion models have achieved remarkable generative capabilities, yet accurately aligning complex textual prompts with synthesized layouts remains an ongoing challen…
cs.CV2026
-Sampling: Zero-Cost Zigzag Trajectories for Semantic Alignment in Diffusion Models
Haosen Li, Wenshuo Chen, Shaofeng Liang +3
Diffusion models have achieved unprecedented success in text-aligned generation, largely driven by Classifier-Free Guidance (CFG). However, standard CFG operates strictly on instan…
eess.SY2026
Physics-Aware LLM-Based Probabilistic Wind Power Scenario Generation under Extreme Icing Conditions
Lei Wang, Ying Zhang, Di Shi +1
Accurately characterizing wind power uncertainty under icing and post-disaster conditions remains a critical challenge for resilient power system operation. To address this issue,…