# CMAG: Concept-Scaffolded Retrieval for Marketplace Avatar Generation

arXiv: https://arxiv.org/abs/2605.18680 · HTML: https://mlsanity.com/paper/2605.18680/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 16 references that are in the map.
- First posted on arXiv 18 May 2026.

## Builds on (most cited first, 13 of 13)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025)
- [The Faiss library](https://mlsanity.com/paper/2401.08281/) (2024)
- [Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation](https://mlsanity.com/paper/2501.12202/) (2025)
- [Generating CAD Code with Vision-Language Models for 3D Designs](https://mlsanity.com/paper/2410.05340/) (2024)
- [Localized Concept Erasure for Text-to-Image Diffusion Models Using Training-Free Gated Low-Rank Adaptation](https://mlsanity.com/paper/2503.12356/) (2025)
- [LL3M: Large Language 3D Modelers](https://mlsanity.com/paper/2508.08228/) (2025)
- [Eval3D: Interpretable and Fine-grained Evaluation for 3D Generation](https://mlsanity.com/paper/2504.18509/) (2025)
- [IP-Composer: Semantic Composition of Visual Concepts](https://mlsanity.com/paper/2502.13951/) (2025)
- [Deep Geometric Moments Promote Shape Consistency in Text-to-3D Generation](https://mlsanity.com/paper/2408.05938/) (2024)
- [Learning Low-Rank Feature for Thorax Disease Classification](https://mlsanity.com/paper/2404.18933/) (2024)
- [DecompDreamer: A Composition-Aware Curriculum for Structured 3D Asset Generation](https://mlsanity.com/paper/2503.11981/) (2025)

## Abstract (arXiv)

Metaverse platforms rely on creator-driven marketplaces where avatars are assembled from discrete, taxonomy-labeled 3D assets (e.g., tops, bottoms, shoes, accessories) under strict category and topology constraints. While users increasingly expect free-form text control, text-only retrieval is brittle: natural language is ambiguous with respect to platform taxonomies, metadata is often noisy or informal, and independently retrieved components can be stylistically inconsistent or geometrically incompatible. We propose CMAG, a concept-scaffolded retrieval and verified composition framework for marketplace avatar generation. Given a prompt, CMAG first synthesizes an intermediate 3D concept scaffold that disambiguates intent beyond text by providing global spatial and stylistic context. In parallel, a view-aware part discovery module extracts localized visual evidence via prompt decomposition and text-grounded segmentation. A prompt-conditioned taxonomy router enforces category coverage and resolves semantic-to-taxonomic mismatch, after which a hybrid category-wise retriever combines part-based fusion with a concept-residual fallback using feature suppression. Finally, an agentic vision--language model filters and re-ranks candidates across categories and drives an iterative verification loop to assemble prompt-faithful, topologically consistent avatars from catalog assets. We evaluate CMAG on diverse compositional prompts and demonstrate improved retrieval robustness and compositional correctness compared to strong baselines, highlighting the importance of 3D concept scaffolding under prompt ambiguity.