paper-with-me

Papers

Video2Code: Generating Interactive Webpages from UI Videos via Action-Aware Revisit

2026-06-16 · Mingde Xu, Zhen Yang, Yan Wang, Yu Wang, Xijun Liu, Zijun Dou, Wenyi Hong, Xiaotao Gu, Bin Xu, Jie Tang arxiv

UI videos provide a natural input for generating interactive webpages, as they capture both webpage appearance and action-triggered state transitions. However, directly applying video-capable vision-language models to this task remains insufficient. Existing models typically rely on sparse sampling or compressed temporal representations, which may miss short action boundaries and break the state-action-state transitions needed to implement webpage behavior. We formulate UI video-to-code generation as executable state-transition recovery from interaction videos, and identify this failure mode as state-transition misalignment. We introduce Video2Code, an action-aware video-to-code approach for recovering executable UI state transitions. Rather than allocating the visual budget uniformly across the video, Video2Code first performs coarse video understanding to locate action-critical regions, then invokes a temporal clipping tool to revisit these regions at higher temporal resolution before generating HTML/CSS/JavaScript code. We instantiate Video2Code with action-aligned video-code supervision and evaluate it under both visual and functional criteria. Experiments show that Video2Code substantially strengthens the underlying open-source model for UI video-to-code generation, improving functional correctness over direct video observation, especially on dense multi-step interactions.

📄 PDF Abstract BibTeX arXiv:2606.20711

Code (0)

등록된 구현이 없습니다.

Tasks

Code Generation

Similar Papers 제목 키워드 기반

IWR-Bench: Can LVLMs reconstruct interactive webpage from a user interaction video?

2025-09-29 · Yang Chen, Minghao Liu, Yufan Shen, Yunwen Li 외 arxiv

The webpage-to-code task requires models to understand visual representations of webpages and generate corresponding code. However, existing benchmarks primarily focus on static screenshot-to-code tasks, thereby overlook…

Code Generation

Interaction2Code: Benchmarking MLLM-based Interactive Webpage Code Generation from Interactive Prototyping

2024-11-05 · Jingyu Xiao, Yuxuan Wan, Yintong Huo, Zixin Wang 외

Multimodal Large Language Models (MLLMs) have demonstrated remarkable performance on the design-to-code task, i.e., generating UI code from UI mock-ups. However, existing benchmarks only contain static web pages for eval…

BenchmarkingCode Generation

Benchmarking Multimodal LLMs on Code Generation for Complex Interactive Webpages

2026-05-29 · Fan Wu, Lishuai Dong, Cuiyun Gao, Yujia Chen 외 arxiv

Recent advancements in multimodal large language models (MLLMs) have achieved remarkable progress in multimodal reasoning and code generation, catalyzing a new paradigm for front-end development. In particular, these mod…

Multimodal ReasoningCode Generation

Animation2Code: Evaluating Temporal Visual Reasoning in Video-to-Code Generation

2026-06-26 · Anya Ji, Abhijith Varma Mudunuri, David M. Chan, Alane Suhr arxiv

While recent vision-language models (VLMs) have achieved significant improvements on static visual-to-code tasks such as generating code for webpages, charts, or SVGs, it remains unclear whether they can recover temporal…

Visual ReasoningCode Generation

WebVR: Benchmarking Multimodal LLMs for WebPage Recreation from Videos via Human-Aligned Visual Rubrics

2026-03-11 · Yuhong Dai, Yanlin Lai, Mitt Huang, Hangyu Guo 외 arxiv

Existing web-generation benchmarks rely on text prompts or static screenshots as input. However, videos naturally convey richer signals such as interaction flow, transition timing, and motion continuity, which are essent…