DiffusionBlocks: Blockwise Training for Generative Models via Score-Based Diffusion
Training large neural networks with end-to-end backpropagation creates significant memory bottlenecks, limiting accessibility to state-of-the-art AI research. We propose $\textit{DiffusionBlocks}$, a novel training framework that interprets neural network blocks as performing denoising operations in a continuous-time diffusion process. By partitioning the network into independently trainable blocks and optimizing noise level assignments based on equal cumulative probability mass, our approach achieves significant memory efficiency while maintaining competitive performance compared to traditional backpropagation in generative tasks. Experiments on image generation and language modeling tasks demonstrate memory reduction proportional to the number of blocks while achieving superior performance. DiffusionBlocks provides a promising pathway for democratizing access to large-scale neural network training with limited computational resources.
Code (0)
등록된 구현이 없습니다.
Tasks
DenoisingImage GenerationLanguage ModelingLanguage ModellingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Blockwise SFT for Diffusion Language Models: Reconciling Bidirectional Attention and Autoregressive Decoding
Discrete diffusion language models have shown strong potential for text generation, yet standard supervised fine-tuning (SFT) misaligns with their semi-autoregressive inference: training randomly masks tokens across the …
Text GenerationOn the Trainability of Masked Diffusion Language Models via Blockwise Locality
Masked diffusion language models (MDMs) have recently emerged as a promising alternative to standard autoregressive large language models (AR-LLMs), yet their optimization can be substantially less stable. We study block…
Coarse-Grained Kullback--Leibler Control of Diffusion-Based Generative AI
Diffusion models and score-based generative models provide a powerful framework for synthesizing high-quality images from noise. However, there is still no satisfactory theory that describes how coarse-grained quantities…
BlockGen: Flexible Blockwise Sequence Modeling with Hybrid Samplers
Is the uniform-state diffusion framework a more powerful paradigm for discrete diffusion? Recent studies indicate that this may be the case. In combination with predictor-corrector samplers, uniform-state diffusion model…
When to Commit? Towards Variable-Size Self-Contained Blocks for Discrete Diffusion Language Models
Discrete diffusion language models (dLLMs) enable parallel token updates with bidirectional attention, yet practical generation typically adopts blockwise semi-autoregressive decoding. This switch creates a training-infe…