List पर वापस जाएँ
📄Papers

Learning to Detect UI Principle Violations via Reinforcement Learning

Mehta N. et al.
2026-07

परिचय

जुलाई 2026 का paper, जो generated web interfaces के लिए lightweight vision-language critic पर केंद्रित है। Authors WCAG 2.2 accessibility, deceptive design और cognitive usability को समेटने वाले 19 principles को एक साथ लाते हैं, फिर लगभग 10,000 generated pages पर verified synthetic violations के साथ training करते हैं।

सारांश

यह paper क्या नया संकेत देता है:

1. Correctness से आगे quality: केवल code चलने की बजाय जाँचता है कि generated interfaces उपयोगी और जिम्मेदार भी हैं या नहीं
2. व्यापक design coverage: Accessibility, deceptive-pattern, perception, cognition और interaction principles को जोड़ता है
3. Reproducible data pipeline: अलग-अलग LLM-generated Tailwind pages में ज्ञात violations डालकर verify करता है
4. Efficient critic: 19-principle benchmark पर 4B vision-language model को 36% से 84% micro-F1 तक सुधारता है
5. Generation-loop utility: बेहतर UI generators के लिए critic को audit gate, training-data filter और reward signal की तरह रखता है

Tags

ui-evaluationaccessibilitydesign-qualityvision-language-modelreinforcement-learning
मूल लेख पढ़ें

मिलते-जुलते लेख

📄Papers

Toward Frontier-Quality Declarative UI Generation at Small-Model Cost

September 2026 Harness4GenUI paper studying whether small language models can generate production-oriented A2UI from approved component catalogs. Across task-management and cloud-console domains, the authors compare training-data strategies, model sizes, catalog sizes, cost, latency, binding correctness, and rendered quality.

a2uismall-language-modelssupervised-fine-tuning
लेखक Yang Y. et al. · 2026-09
और पढ़ें
📄Papers

EvoGenUI-Bench: Evaluating Multi-Turn Generative UI Assistants

August 2026 benchmark testing whether LLM assistants can maintain one executable web interface as user requirements evolve. EvoGenUI-Bench contains 150 five-turn tasks across information presentation, stateful interaction, and tool-grounded external state, with browser-based evaluation over screenshots, DOM and source evidence, actor traces, and runtime logs.

generative-uimulti-turnbenchmark
लेखक Peng Y. et al. · 2026-08
और पढ़ें
📄Papers

Maru: Information Architecture for Aligned, Persistent Generative UI

August 2026 HCI paper introducing information architecture as shared state for Generative UI. Maru captures how users partition, order, name, and prioritize information, turns those choices into persistent rules, and applies them across successive interface generations instead of rebuilding structure from each prompt.

generative-uiinformation-architecturepersonalization
लेखक Kim E. et al. · 2026-08
और पढ़ें

Generative UI resources का curated संग्रह।

बनाया गया ❤️ community द्वारा