# MANTA -- Model Adapter Native generations that's Affordable

arXiv: https://arxiv.org/abs/2409.14363 · HTML: https://mlsanity.com/paper/2409.14363/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 34 references that are in the map.
- First posted on arXiv 22 Sep 2024.

## Builds on (most cited first, 19 of 19)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Diffusion Model Alignment Using Direct Preference Optimization](https://mlsanity.com/paper/2311.12908/) (2023)
- [Reliable Fidelity and Diversity Metrics for Generative Models](https://mlsanity.com/paper/2002.09797/) (2020)
- [Aligning Text-to-Image Diffusion Models with Reward Backpropagation](https://mlsanity.com/paper/2310.03739/) (2023)
- [A Survey on Efficient Inference for Large Language Models](https://mlsanity.com/paper/2404.14294/) (2024)
- [Improving Retrieval for RAG based Question Answering Models on Financial Documents](https://mlsanity.com/paper/2404.07221/) (2024)
- [Reasoning in Token Economies: Budget-Aware Evaluation of LLM Reasoning Strategies](https://mlsanity.com/paper/2406.06461/) (2024)
- [Fast and Accurate Factual Inconsistency Detection Over Long Documents](https://mlsanity.com/paper/2310.13189/) (2023)
- [Diffusion Model with Perceptual Loss](https://mlsanity.com/paper/2401.00110/) (2023)
- [Organic or Diffused: Can We Distinguish Human Art from AI-generated Images?](https://mlsanity.com/paper/2402.03214/) (2024)
- [Stylus: Automatic Adapter Selection for Diffusion Models](https://mlsanity.com/paper/2404.18928/) (2024)
- [Explaining generative diffusion models via visual analysis for interpretable decision-making process](https://mlsanity.com/paper/2402.10404/) (2024)
- [Exploring the Impact of AI-generated Image Tools on Professional and Non-professional Users in the Art and Design Fields](https://mlsanity.com/paper/2406.10640/) (2024)
- [Increased Compute Efficiency and the Diffusion of AI Capabilities](https://mlsanity.com/paper/2311.15377/) (2023)
- [Simple Drop-in LoRA Conditioning on Attention Layers Will Improve Your Diffusion Model](https://mlsanity.com/paper/2405.03958/) (2024)

## Abstract (arXiv)

The presiding model generation algorithms rely on simple, inflexible adapter selection to provide personalized results. We propose the model-adapter composition problem as a generalized problem to past work factoring in practical hardware and affordability constraints, and introduce MANTA as a new approach to the problem. Experiments on COCO 2014 validation show MANTA to be superior in image task diversity and quality at the cost of a modest drop in alignment. Our system achieves a 94% win rate in task diversity and a 80% task quality win rate versus the best known system, and demonstrates strong potential for direct use in synthetic data generation and the creative art domains.