SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2502.17793 · ACL · 2025

SYNTHIA: Novel Concept Design with Affordance Composition

Kai-Wei Chang, Khanh Nguyen, Nanyun Peng, Jeonghwan Kim, Heng Ji, Hyeonjeong Ha, Zhenhailong Wang, Ansel Blume, Jiateng Liu, Jin Xiaomeng

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 1 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
HyeonjeongHa/SYNTHIA — 0 of 1
FunctionStatusWhere it lives
affordance_sampling Not yet run HyeonjeongHa/SYNTHIA/gen_curriculum.py
pointer only (licence: NONE) · get_code("abebfee3ca629923")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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 visually novel and 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. Code is available at https://github.com/HyeonjeongHa/SYNTHIA.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2502.17793")
get_code_for_paper("2502.17793")
have("2502.17793")

Connect an agent — have() is free.