2 papers
cs.CV2026
Vision as Unified Multimodal Generation
Xiaoyang Han, Jianhua Li, Kewang Deng +14
We formulate computer vision as unified multimodal generation, where heterogeneous visual tasks are expressed in the native text and image generation spaces of a unified multimodal…
cs.LG2026
Seeing Before Reasoning: Decoupling Perception and Reasoning for Shortcut-Resilient Multimodal On-Policy Self-Distillation
Sihan Wang, Xiyao Liu, Lianqing Liu +1
On-policy self-distillation (OPSD) trains a model on its own rollouts and uses a frozen copy to provide dense token-level targets conditioned on a reference target. This works well…