CRAFT: Aligning Diffusion Models with Fine-Tuning Is Easier Than You Think

• URL: http://arxiv.org/abs/2603.18991v1
• Date: Thu, 19 Mar 2026 14:59:46 GMT
• Title: CRAFT: Aligning Diffusion Models with Fine-Tuning Is Easier Than You Think
• Abstract summary: We propose Composite Reward Assisted Fine-Tuning (CRAFT) to generate high-quality, human preference-aligned images.<n>CRAFT is a lightweight yet powerful fine-tuning paradigm that requires significantly reduced training data while maintaining computational efficiency.<n>Our empirical results demonstrate that CRAFT with only 100 samples can easily outperform recent SOTA preference optimization methods with thousands of preference-paired samples.
• Score: 20.279525179138453
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Aligning Diffusion models has achieved remarkable breakthroughs in generating high-quality, human preference-aligned images. Existing techniques, such as supervised fine-tuning (SFT) and DPO-style preference optimization, have become principled tools for fine-tuning diffusion models. However, SFT relies on high-quality images that are costly to obtain, while DPO-style methods depend on large-scale preference datasets, which are often inconsistent in quality. Beyond data dependency, these methods are further constrained by computational inefficiency. To address these two challenges, we propose Composite Reward Assisted Fine-Tuning (CRAFT), a lightweight yet powerful fine-tuning paradigm that requires significantly reduced training data while maintaining computational efficiency. It first leverages a Composite Reward Filtering (CRF) technique to construct a high-quality and consistent training dataset and then perform an enhanced variant of SFT. We also theoretically prove that CRAFT actually optimizes the lower bound of group-based reinforcement learning, establishing a principled connection between SFT with selected data and reinforcement learning. Our extensive empirical results demonstrate that CRAFT with only 100 samples can easily outperform recent SOTA preference optimization methods with thousands of preference-paired samples. Moreover, CRAFT can even achieve 11-220$\times$ faster convergences than the baseline preference optimization methods, highlighting its extremely high efficiency.

Related papers

• Convex Optimization for Alignment and Preference Learning on a Single GPU [52.997197698288936]
  Fine-tuning large language models to align with human preferences has driven the success of systems such as Gemini and ChatGPT.<n>Direct Preference Optimization (DPO) offers a simpler alternative but has limitations such as inconsistent ranking accuracy and high dependence on GPU resources.<n>We propose the Convex Optimization for Alignment and Preference Learning Algorithm (COALA), a novel lightweight strategy with strong theoretical guarantees.
  arXiv  Detail & Related papers  (2026-05-22T05:25:00Z)
• Unified Data Selection for LLM Reasoning [66.0118347918729]
  Training Large Language Models (LLMs) for complex, long-CoT reasoning is often bottlenecked by the need for massive high-quality reasoning data.<n>We propose High-Entropy Sum (HES), a training-free metric that quantifies reasoning quality by summing only the entropy of the top (e.g., 0.5%) highest-entropy tokens in each reasoning sample.
  arXiv  Detail & Related papers  (2026-05-21T12:21:41Z)
• TLoRA+: A Low-Rank Parameter-Efficient Fine-Tuning Method for Large Language Models [4.092357804635167]
  We propose a novel PEFT method that incorporates the TLoRA+ into the weight matrices of pre-trained models.<n>The proposed approach not only preserves the efficiency of low-rank adaptation but also further enhances performance without significantly increasing computational cost.
  arXiv  Detail & Related papers  (2026-04-15T00:30:57Z)
• Utility-Diversity Aware Online Batch Selection for LLM Supervised Fine-tuning [49.04912820721943]
  Supervised fine-tuning (SFT) is computationally expensive and sometimes suffers from overfitting or bias amplification.<n>This work studies the online batch selection family that dynamically scores and filters samples during the training process.<n>We develop textbfUDS (Utility-Diversity Sampling), a framework for efficient online batch selection in SFT.
  arXiv  Detail & Related papers  (2025-10-19T15:32:01Z)
• InfiAlign: A Scalable and Sample-Efficient Framework for Aligning LLMs to Enhance Reasoning Capabilities [27.09178257629886]
  InfiAlign is a scalable and sample-efficient post-training framework for large language models (LLMs)<n>At the core of InfiAlign is a robust data selection pipeline that automatically curates high-quality alignment data from open-source reasoning.<n>Our results highlight the effectiveness of combining principled data selection with full-stage post-training.
  arXiv  Detail & Related papers  (2025-08-07T15:34:06Z)
• Ultra-Resolution Adaptation with Ease [62.56434979517156]
  We propose a set of key guidelines for ultra-resolution adaptation termed emphURAE.<n>We show that tuning minor components of the weight matrices outperforms widely-used low-rank adapters when synthetic data are unavailable.<n>Experiments validate that URAE achieves comparable 2K-generation performance to state-of-the-art closed-source models like FLUX1.1 [Pro] Ultra with only 3K samples and 2K iterations.
  arXiv  Detail & Related papers  (2025-03-20T16:44:43Z)
• Discriminative Finetuning of Generative Large Language Models without Reward Models and Human Preference Data [73.04828796123581]
  Supervised fine-tuning (SFT) has become a crucial step for aligning pretrained large language models (LLMs)<n>We introduce Discriminative Fine-Tuning (DFT), an improved variant of SFT, which mitigates the burden of collecting human-labeled preference data.<n>Our contributions include: (i) a discriminative probabilistic framework for fine-tuning LLMs by explicitly modeling the discriminative likelihood of an answer among all possible outputs given an input; (ii) efficient algorithms to optimize this discriminative likelihood; and (iii) extensive experiments demonstrating DFT's effectiveness
  arXiv  Detail & Related papers  (2025-02-25T22:38:55Z)
• Preference-Oriented Supervised Fine-Tuning: Favoring Target Model Over Aligned Large Language Models [12.500777267361102]
  We introduce a novel textbfpreference-textbforiented supervised textbffine-textbftuning approach, namely PoFT.<n>The intuition is to boost SFT by imposing a particular preference: textitfavoring the target model over aligned LLMs on the same SFT data.<n>PoFT achieves stable and consistent improvements over the SFT baselines across different training datasets and base models.
  arXiv  Detail & Related papers  (2024-12-17T12:49:14Z)
• Bridging SFT and DPO for Diffusion Model Alignment with Self-Sampling Preference Optimization [67.8738082040299]
  Self-Sampling Preference Optimization (SSPO) is a new alignment method for post-training reinforcement learning.<n>SSPO eliminates the need for paired data and reward models while retaining the training stability of SFT.<n>SSPO surpasses all previous approaches on the text-to-image benchmarks and demonstrates outstanding performance on the text-to-video benchmarks.
  arXiv  Detail & Related papers  (2024-10-07T17:56:53Z)
• ASFT: Aligned Supervised Fine-Tuning through Absolute Likelihood [14.512464277772194]
  Aligned Supervised Fine-Tuning (ASFT) is an effective approach that better aligns Large Language Models with pair-wise datasets. ASFT mitigates the issue where the DPO loss function decreases the probability of generating human-dispreferred data. Extensive experiments demonstrate that ASFT is an effective alignment approach, consistently outperforming existing methods.
  arXiv  Detail & Related papers  (2024-09-14T11:39:13Z)
• Triple Preference Optimization: Achieving Better Alignment using a Single Step Optimization [34.29965046863887]
  Triple Preference Optimization (TPO) is a new preference learning method designed to enhance both reasoning and instruction-following abilities.<n>TPO achieves significant improvements over existing methods without substantially increasing response length across different dataset sizes.
  arXiv  Detail & Related papers  (2024-05-26T20:18:11Z)
• CAFE: Learning to Condense Dataset by Aligning Features [72.99394941348757]
  We propose a novel scheme to Condense dataset by Aligning FEatures (CAFE) At the heart of our approach is an effective strategy to align features from the real and synthetic data across various scales. We validate the proposed CAFE across various datasets, and demonstrate that it generally outperforms the state of the art.
  arXiv  Detail & Related papers  (2022-03-03T05:58:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.