# SYNTHIA: Novel Concept Design with Affordance Composition

arXiv: https://arxiv.org/abs/2502.17793 · HTML: https://mlsanity.com/paper/2502.17793/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 32 references that are in the map.
- First posted on arXiv 25 Feb 2025.

## Builds on (most cited first, 18 of 18)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation](https://mlsanity.com/paper/2402.05054/) (2024)
- [Prometheus: Inducing Fine-grained Evaluation Capability in Language Models](https://mlsanity.com/paper/2310.08491/) (2023)
- [InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuning](https://mlsanity.com/paper/2304.03411/) (2023)
- [StyleDrop: Text-to-Image Generation in Any Style](https://mlsanity.com/paper/2306.00983/) (2023)
- [RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion Paths](https://mlsanity.com/paper/2305.18295/) (2023)
- [Large-scale Text-to-Image Generation Models for Visual Artists' Creative Works](https://mlsanity.com/paper/2210.08477/) (2022)
- [Concept Decomposition for Visual Exploration and Inspiration](https://mlsanity.com/paper/2305.18203/) (2023)
- [ConceptLab: Creative Concept Generation using VLM-Guided Diffusion Prior Constraints](https://mlsanity.com/paper/2308.02669/) (2023)
- [Kandinsky 3: Text-to-Image Synthesis for Multifunctional Generative Framework](https://mlsanity.com/paper/2410.21061/) (2024)
- [Inkspire: Supporting Design Exploration with Generative AI through Analogical Sketching](https://mlsanity.com/paper/2501.18588/) (2025)
- [Visual Concept-driven Image Generation with Text-to-Image Diffusion Model](https://mlsanity.com/paper/2402.11487/) (2024)
- [A Novel Idea Generation Tool using a Structured Conversational AI (CAI) System](https://mlsanity.com/paper/2409.05747/) (2024)
- [Inspired by AI? A Novel Generative AI System To Assist Conceptual Automotive Design](https://mlsanity.com/paper/2407.11991/) (2024)

## Built on by (most cited first, 4 of 4)

- [PARTONOMY: Large Multimodal Models with Part-Level Visual Understanding](https://mlsanity.com/paper/2505.20759/) (2025)
- [A Creative Agent is Worth a 64-Token Template](https://mlsanity.com/paper/2603.17895/) (2026)
- [Assessing the Creativity of Large Language Models: Testing, Limits, and New Frontiers](https://mlsanity.com/paper/2605.13450/) (2026)
- [PairedGTA: Generating Driving Datasets for Controlled Photometric Shift Analysis](https://mlsanity.com/paper/2606.01192/) (2026)

## Abstract (arXiv)

Text-to-image (T2I) models enable rapid concept design, making them widely used in AI-driven design. While recent studies focus on generating semantic and stylistic variations of given design concepts, functional coherence--the integration of multiple affordances into a single coherent concept--remains largely overlooked. In this paper, we introduce SYNTHIA, a framework for generating novel, functionally coherent designs based on desired affordances. Our approach leverages a hierarchical concept ontology that decomposes concepts into parts and affordances, serving as a crucial building block for functionally coherent design. We also develop a curriculum learning scheme based on our ontology that contrastively fine-tunes T2I models to progressively learn affordance composition while maintaining visual novelty. To elaborate, we (i) gradually increase affordance distance, guiding models from basic concept-affordance association to complex affordance compositions that integrate parts of distinct affordances into a single, coherent form, and (ii) enforce visual novelty by employing contrastive objectives to push learned representations away from existing concepts. Experimental results show that SYNTHIA outperforms state-of-the-art T2I models, demonstrating absolute gains of 25.1% and 14.7% for novelty and functional coherence in human evaluation, respectively.