# Spatula: Exploring On-Demand In-Situ Interfaces and Interaction for Attribute Control

arXiv: https://arxiv.org/abs/2607.10405 · HTML: https://mlsanity.com/paper/2607.10405/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 59 references that are in the map.
- First posted on arXiv 11 Jul 2026.

## Builds on (most cited first, 17 of 17)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Creating General User Models from Computer Use](https://mlsanity.com/paper/2505.10831/) (2025)
- [DynaVis: Dynamically Synthesized UI Widgets for Visualization Editing](https://mlsanity.com/paper/2401.10880/) (2024)
- [CoQuest: Exploring Research Question Co-Creation with an LLM-based Agent](https://mlsanity.com/paper/2310.06155/) (2023)
- [RealitySketch: Embedding Responsive Graphics and Visualizations in AR through Dynamic Sketching](https://mlsanity.com/paper/2008.08688/) (2020)
- [ProactiveVA: Proactive Visual Analytics with LLM-Based UI Agent](https://mlsanity.com/paper/2507.18165/) (2025)
- [LogoMotion: Visually-Grounded Code Synthesis for Creating and Editing Animation](https://mlsanity.com/paper/2405.07065/) (2024)
- [MoVer: Motion Verification for Motion Graphics Animations](https://mlsanity.com/paper/2502.13372/) (2025)
- [CrossTalk: Intelligent Substrates for Language-Oriented Interaction in Video-Based Communication and Collaboration](https://mlsanity.com/paper/2308.03311/) (2023)
- [Augmented Physics: Creating Interactive and Embedded Physics Simulations from Static Textbook Diagrams](https://mlsanity.com/paper/2405.18614/) (2024)
- [Cooperative Design Optimization through Natural Language Interaction](https://mlsanity.com/paper/2508.16077/) (2025)
- [MoGraphGPT: Creating Interactive Scenes Using Modular LLM and Graphical Control](https://mlsanity.com/paper/2502.04983/) (2025)
- [Preference-Guided Multi-Objective UI Adaptation](https://mlsanity.com/paper/2509.18960/) (2025)
- [RealityCanvas: Augmented Reality Sketching for Embedded and Responsive Scribble Animation Effects](https://mlsanity.com/paper/2307.16116/) (2023)
- [Continual Human-in-the-Loop Optimization](https://mlsanity.com/paper/2503.05405/) (2025)
- [Piet: Facilitating Color Authoring for Motion Graphics Video](https://mlsanity.com/paper/2403.02199/) (2024)

## Abstract (arXiv)

Controlling attributes is a critical step toward achieving the final creative outcome, yet current approaches fall short in supporting users in the iterative refinement of generative content. We propose Spatula, a proof-of-concept system that generates on-demand, in-situ attribute control interfaces and interactions for creating motion graphics. Building on a technical probe that automatically analyzes animation context and generates corresponding attributes and UI, we frame attribute control as an explorable landscape and explore the attribute control space along four key dimensions: Discoverability, Resolution, Scope, and Expandability. Findings from a user study (N=12) show that our system provides intuitive and convenient interactions while supporting diverse needs for fine-grained parameter control. Furthermore, our applications demonstrate that the plug-and-play design generalizes to other domains, such as web design and 3D modeling.