arXiv Computer Vision
Rubrics as Visual-Repair Context for Self-Evolving UI-to-Code Generation
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
Hugging Face Trending Papers
Aug 11
VisEditBench: Can Vision-Language Models Edit Visualization Code from Multimodal Feedback?
Vision-language models (VLMs) have shown strong capabilities in generating visualization code from textual or visual specifications. However, real-world visualization authoring is inherently iterative: users frequently revise existing visualizations to repair flawed charts or adapt them to desired styles.
arXiv AI
Jun 10
Self-Distillation Policy Optimization via Visual Feedback: Bridging Code and Visual Artifacts
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.
arXiv AI
Jul 3
COMFYCLAW: Self-Evolving Skill Harnesses for Image Generation Workflows
arXiv:2607. 01709v1 Announce Type: new Abstract: Agents are increasingly used to construct workflows and assist humans in completing recurring tasks more efficiently.
arXiv Machine Learning
Jun 16
REFLEX: Reflective Evolution from LLM Experience
arXiv:2606. 16496v1 Announce Type: cross Abstract: Large multimodal language models (LLMs) have emerged as powerful tools for guiding evolutionary search toward interpretable programmatic policies.
arXiv AI
Jun 16
Imperfect Visual Verification for Code Edition : A Case Study on TikZ
arXiv:2606. 15693v1 Announce Type: cross Abstract: LLMs have significantly advanced code generation, enabling the synthesis of functional programs.
arXiv Computer Vision
Sep 23
Reading Right, Answering Wrong: How Visual Configuration Changes Affect Evidence Use in VLMs
Vision‑language models (VLMs) can lose accuracy when images are resized, even with minimal changes. The study shows that such small visual configuration changes—like tiling or token arrangement—cause more correctness flips across multiple checkpoints and benchmarks. Interestingly, in many cases the models still read the correct answer but fail to use it, and attention interventions reveal that configuration shifts weaken the use of readable information. By guiding models with field cues and their own transcriptions, the authors correct 97.2% of these errors.