AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

From Diagrams to Code: Multilingual Programming with Visual Design

Linzheng Chai, Jian Yang, Shukai Liu, Wei Zhang, Liran WANG, Ke Jin, Tao Sun, Congnan Liu, Chenchen Zhang, Hualei Zhu, Jiaheng Liu, Xianjie Wu and 3 more

ICML 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Interleaved image-text generation with MLLMs

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Introduces a visual-first multilingual code generation setting where models must interpret diagrams (architecture/design visuals) and produce code across multiple programming languages.

Problem

AI coding assistants must interpret diagrams of system architectures across multiple programming languages, but such capability is underdeveloped; the abstract is truncated so the specific gap is only partially stated.

Approach

Frames diagram-to-code generation as a visual-first, multilingual programming task motivated by vibe coding, where architectures are communicated through visual designs before coding.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add stage-2 SFT to Qwen2-VL-Instruct (ablation)Qwen2-VL-7B-Instruct · M2EvalPass@1 avg: 12.0 -> 16.7Improved
add stage-2 SFT to Qwen2-VL-Base (ablation)Qwen2-VL-7B-Base · M2EvalPass@1 avg: - -> 18.0Improved
add stage-1 SFT with vision encoder trained (ablation)Qwen2-VL-7B-Base · M2EvalPass@1 avg: 8.7 (frozen) -> 10.0Improved
add stage-1 SFT before stage-2 SFT (ablation)Qwen2-VL-7B-Base · M2EvalPass@1 avg: 18.0 -> 25.3Improved
add stage-2 SFT after stage-1 SFT (ablation)Qwen2-VL-7B-Base · M2EvalPass@1 avg: 10.0 -> 25.3Improved
use more stage-1 training data before stage-2 (ablation)M2-Coder-7B · M2EvalPass@1Improved
remove the diagram from the input (ablation)DeepSeek-V3 and Qwen2.5-Coder · M2EvalPass@1: to 0.0Hurt
train on M2C-Instruct (two-stage) vs. base instruct modelQwen2-VL-7B · M2EvalPass@1 avg: 12.0 -> 25.3Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy