Tag
This paper investigates the mechanisms behind self-alignment methods in diffusion transformers, revealing that performance improvements from methods like Self-Flow primarily come from data augmentation along the noise dimension rather than token interactions between noise levels. The authors introduce Attention Separation to demonstrate this and propose an effective design combining self-representation alignment with dual-timestep augmentation.
This paper introduces Emergent Alignment, a self-supervised method that endows LLMs with a conscience step to review their own outputs and uses Direct Preference Optimization to steer away from unethical behavior, enabling online alignment without external judges.
LC-ERD is a framework that mines latent logic from LLM-generated reasoning chains to decompose global rewards into step-level signals, enabling self-evolving reasoning without human annotation. It addresses label noise, coarse supervision, and distributional collapse via variational logic potential and multi-agent value decomposition.