paper-with-me

홈 › Papers

Variance-Aware Adaptive Weighting for Diffusion Model Training

2026-03-11 · Nanlong Sun, Lei Shi arxiv

Diffusion models have recently achieved remarkable success in generative modeling, yet their training dynamics across different noise levels remain highly imbalanced, which can lead to inefficient optimization and unstable learning behavior. In this work, we investigate this imbalance from the perspective of loss variance across log-SNR levels and propose a variance-aware adaptive weighting strategy to address it. The proposed approach dynamically adjusts training weights based on the observed variance distribution, encouraging a more balanced optimization process across noise levels. Extensive experiments on CIFAR-10 and CIFAR-100 demonstrate that the proposed method consistently improves generative performance over standard training schemes, achieving lower Fréchet Inception Distance (FID) while also reducing performance variance across random seeds. Additional analysis, including loss-log-SNR visualization, variance heatmaps, and ablation studies, further reveal that the adaptive weighting effectively stabilizes training dynamics. These results highlight the potential of variance-aware training strategies for improving diffusion model optimization.

📄 PDF Abstract BibTeX arXiv:2603.10391

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Variance-Aware Loss Scheduling for Multimodal Alignment in Low-Data Settings

2025-03-05 · Sneh Pillai

Training vision-language models for image-text alignment typically requires large datasets to achieve robust performance. In low-data scenarios, standard contrastive learning can struggle to align modalities effectively …

Contrastive LearningImage-text RetrievalSchedulingText Retrieval

Unsupervised Denoising of Diffusion-Weighted Images with Bias and Variance Corrected Noise Modeling

2026-02-22 · Jine Xie, Zhicheng Zhang, Yunwei Chen, Yanqiu Feng 외 arxiv

Diffusion magnetic resonance imaging (dMRI) plays a vital role in both clinical diagnostics and neuroscience research. However, its inherently low signal-to-noise ratio (SNR), especially under high diffusion weighting, s…

MAPLE: Modality-Aware Post-training and Learning Ecosystem

2026-02-12 · Nikhil Verma, Minjung Kim, JooYoung Yoo, Kyung-Min Jin 외 arxiv

Multimodal language models now integrate text, audio, and video for unified reasoning. Yet existing RL post-training pipelines treat all input signals as equally relevant, ignoring which modalities each task actually req…

Adaptive Non-Uniform Timestep Sampling for Diffusion Model Training

2024-11-15 · Myunsoo Kim, Donghyeon Ki, Seong-Woong Shim, Byung-Jun Lee

As a highly expressive generative model, diffusion models have demonstrated exceptional success across various domains, including image generation, natural language processing, and combinatorial optimization. However, as…

Image GenerationScheduling

Adaptive Non-Uniform Timestep Sampling for Accelerating Diffusion Model Training

2025-01-01 · CVPR 2025 1 · Myunsoo Kim, Donghyeon Ki, Seong-Woong Shim, Byung-Jun Lee

As a highly expressive generative model, diffusion models have demonstrated exceptional success across various domains, including image generation, natural language processing, and combinatorial optimization. However…

Combinatorial OptimizationImage GenerationScheduling