Video2Code adds action-aware temporal clipping to video-language models to better recover executable state transitions when turning UI videos into HTML/CSS/JS code.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Visual-SDPO distills visual feedback from rendered code outputs into a student policy via grounded credit weighting and GRPO, yielding over 10-point gains on chart/UI/slide benchmarks.
ArkTrans achieves up to 90.67% compilable ArkUI translations from KJC/SwiftUI using heuristic LLM guidance and empirical post-fixing rules, versus 0% for direct or one-shot prompting on a 100-sample benchmark.
citing papers explorer
-
Video2Code: Generating Interactive Webpages from UI Videos via Action-Aware Revisit
Video2Code adds action-aware temporal clipping to video-language models to better recover executable state transitions when turning UI videos into HTML/CSS/JS code.
-
Self-Distillation Policy Optimization via Visual Feedback: Bridging Code and Visual Artifacts
Visual-SDPO distills visual feedback from rendered code outputs into a student policy via grounded credit weighting and GRPO, yielding over 10-point gains on chart/UI/slide benchmarks.
-
Porting Declarative UI to HarmonyOS: A Heuristic-guided LLM Approach
ArkTrans achieves up to 90.67% compilable ArkUI translations from KJC/SwiftUI using heuristic LLM guidance and empirical post-fixing rules, versus 0% for direct or one-shot prompting on a 100-sample benchmark.