The European Commission today presented the European Technological Sovereignty Package, a set of measures to strengthen Europe\'s capacity in semiconductors, artificial intelligence (AI), cloud and open source.

This systematic literature review examines the role of large language models (LLMs) in UI/UX design, synthesizing findings from 38 peer-reviewed studies published between 2022 and 2025. We identify key LLMs in use, including GPT-4, Gemini, and PaLM, and map their integration across the design lifecycle, from ideation to evaluation. Common practices include prompt engineering, human-in-the-loop workflows, and multimodal input. While LLMs are reshaping design processes, challenges such as hallucination, prompt instability, and limited explainability persist. Our findings highlight LLMs as emerging collaborators in design, and we propose directions for the ethical, inclusive, and effective integration of these technologies.

Generative UI is transforming interface design by facilitating AI-driven collaborative workflows between designers and computational systems. This study establishes a working definition of Generative UI through a multi-method qualitative approach, integrating insights from a systematic literature review of 127 publications, expert interviews with 18 participants, and analyses of 12 case studies. Our findings identify five core themes that position Generative UI as an iterative and co-creative process. We highlight emerging design models, including hybrid creation, curation-based workflows, and AI-assisted refinement strategies. Additionally, we examine ethical challenges, evaluation criteria, and interaction models that shape the field. By proposing a conceptual foundation, this study advances both theoretical discourse and practical implementation, guiding future HCI research toward responsible and effective generative UI design practices.

As artificial intelligence (AI) continues to evolve from a back-end computational tool into an interactive, generative collaborator, its integration into early-stage design processes demands a rethinking of traditional workflows in human-centered design. This paper explores the emergent paradigm of human-AI co-creation, where AI is not merely used for automation or efficiency gains, but actively participates in ideation, visual conceptualization, and decision-making. Specifically, we investigate the use of large language models (LLMs) like GPT-4 and multimodal diffusion models such as Stable Diffusion as creative agents that engage designers in iterative cycles of proposal, critique, and revision.

Multimodal Large Language Models have demonstrated exceptional performance in UI2Code tasks, significantly enhancing website development efficiency. However, these tasks incur substantially higher computational overhead than traditional code generation due to the large number of input image tokens and extensive output code tokens required. Our comprehensive study identifies significant redundancies in both image and code tokens that exacerbate computational complexity and hinder focus on key UI elements, resulting in excessively lengthy and often invalid HTML files. We propose EfficientUICoder, a compression framework for efficient UI code generation with three key components. First, Element and Layout-aware Token Compression preserves essential UI information by detecting element regions and constructing UI element trees. Second, Region-aware Token Refinement leverages attention scores to discard low-attention tokens from selected regions while integrating high-attention tokens from unselected regions. Third, Adaptive Duplicate Token Suppression dynamically reduces repetitive generation by tracking HTML/CSS structure frequencies and applying exponential penalties. Extensive experiments show EfficientUICoderachieves a 55%-60% compression ratio without compromising webpage quality and delivers superior efficiency improvements: reducing computational cost by 44.9%, generated tokens by 41.4%, prefill time by 46.6%, and inference time by 48.8% on 34B-level MLLMs. Code is available at https://github.com/WebPAI/EfficientUICoder.

Although Multimodal Large Language Models (MLLMs) have been widely applied across domains, they are still facing challenges in domain-specific tasks, such as User Interface (UI) understanding accuracy and UI generation quality. In this paper, we introduce UI-UG (a unified MLLM for UI Understanding and Generation), integrating both capabilities. For understanding tasks, we employ Supervised Fine-tuning (SFT) combined with Group Relative Policy Optimization (GRPO) to enhance fine-grained understanding on the modern complex UI data. For generation tasks, we further use Direct Preference Optimization (DPO) to make our model generate human-preferred UIs. In addition, we propose an industrially effective workflow, including the design of an LLM-friendly domain-specific language (DSL), training strategies, rendering processes, and evaluation metrics. In experiments, our model achieves state-of-the-art (SOTA) performance on understanding tasks, outperforming both larger general-purpose MLLMs and similarly-sized UI-specialized models. Our model is also on par with these larger MLLMs in UI generation performance at a fraction of the computational cost. We also demonstrate that integrating understanding and generation tasks can improve accuracy and quality for both tasks. Code and Model: https://github.com/neovateai/UI-UG

Design2Code is the first real-world benchmark for automated front-end engineering from visual designs. Researchers manually...

Large language models (LLMs) promise to accelerate UI design, yet current tools struggle with two fundamentals: externalizing designers' intent and controlling iterative change. We introduce SPEC, a structured, parameterized, hierarchical intermediate representation that exposes UI elements as controllable parameters. Building on SPEC, we present SpecifyUI, an interactive system that extracts SPEC from UI references via region segmentation and vision-language models, composes UIs across multiple sources, and supports targeted edits at global, regional, and component levels. A multi-agent generator renders SPEC into high-fidelity designs, closing the loop between intent expression and controllable generation. Quantitative experiments show SPEC-based generation more faithfully captures reference intent than prompt-based baselines. In a user study with 16 professional designers, SpecifyUI significantly outperformed Stitch on intent alignment, design quality, controllability, and overall experience in human-AI co-creation. Our results position SPEC as a specification-driven paradigm that shifts LLM-assisted design from one-shot prompting to iterative, collaborative workflows.

This article warns that the AI industry is repeating historical security failures by normalizing over-reliance on LLM outputs...

This article describes a technique for using LLMs as classifiers by extracting hidden states rather than generating text. The...

Locofy is an AI tool that converts your Figma and Penpot designs into production-ready code. It streamlines frontend development...

A practical guide to building a local, privacy-first screenshot organizer using LMStudio’s Python SDK and Gemma 3 multimodal...

A deep dive into consciousness through computational and structural lenses, exploring how self-modeling systems create the illusion of certainty. Relevant to AI systems design, interpretability, and understanding emergent properties in complex systems.

An open-source specification and ecosystem for building multi-provider, interoperable LLM interfaces. Enables builders to work with different AI providers using a unified schema, streaming events, and tool integration.

AI-native design tool with first-class agent support. Features artboards, layers, auto-layout, and 66 integrated MCP tools for AI-powered design workflows. Free to use.

Text-to-image models now generate graphic design at production scale, yet their supervision still comes primarily from photo-style preference datasets with a single overall verdict per comparison. Designers evaluate designs along several distinct axes (e.g., typography, layout, color harmony) that a single preference label collapses. We release \emph{TASTE} \textit{(Typography, Aesthetics, Spatial, Tone, Etc.)}, a multi-dimensional preference dataset in which two disjoint cohorts of five professional designers each ranked outputs from four current text-to-image models across nine criteria along with per-image hallucination flags. We pair the dataset with two contributions. First, a criterion-agnostic signal-validation framework based on Kendall's $τ$, majority-vote probability, and Condorcet cycles against exact iid-uniform nulls; the analysis reveals significant but moderate designer agreement, with every TASTE criterion rejecting the random-rater null. Second, we benchmark preference models on TASTE and find that off-the-shelf VLM judges and dedicated T2I scorers fail to reach majority agreement with the designer panel, while a small MLP head trained directly on TASTE substantially narrows the gap to the single-rater ceiling, setting a baseline for future TASTE-trained preference models.

A design vocabulary and CLI tool for AI coding agents. Features 23 design commands, anti-pattern detection with 44 rules, and integration with Claude Code, Cursor, GitHub Copilot, and other AI platforms. Eliminates generic design outputs and maintains consistent design standards.

How LLMs are enabling a new generation of sophisticated scams at scale. Explores the gap between cheap mass-market schemes and expensive targeted attacks, and how AI makes personalized social engineering affordable and automatable.

Discussion on Hacker News examining whether larger language models necessarily hallucinate more and if scaling laws have plateaued.

A real filesystem abstraction for AI memory with a single binary. No SDK or vector database required - simple persistent storage for LLM context and memory.

Sakana AI is an AI research laboratory based in Tokyo, Japan, dedicated to building next-generation foundation models through...

Research benchmark comparing open-weight and frontier AI models on vulnerability detection. GLM 5.2 outperformed Claude Code by 7 points on IDOR detection at 1/6 the cost, demonstrating that open-weight models are becoming viable alternatives for security applications.