arXiv AI By Haoyu Dong

Self-Distillation Policy Optimization via Visual Feedback: Bridging Code and Visual Artifacts

Read the original on arXiv AI →

arXiv:2606. 10334v1 Announce Type: new Abstract: Code-generating large language models (LLMs) increasingly produce visual artifacts such as charts, web pages, and slides by writing programs that are executed by non-differentiable renderers, committing to code before observing the render.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

Hugging Face Trending Papers
Aug 10

Perception Before Supervision: Self-Contained Visual Distillation from Counterfactual Blind Spots

Self-improvement for multimodal large language models (MLLMs) is typically driven by reward-based methods that provide only coarse scalar feedback. Distillation offers a richer alternative through dense token-level supervision, but in the visual domain it usually depends on privileged context constructed using external annotations and tools, or stronger models.