TensorX
返回文献探索

Paper · arXiv 2604.09168

ELT: Elastic Looped Transformers for Visual Generation

Sahil Goyal, Swayam Agrawal, Gautham Govind Anil, Prateek Jain, Sujoy Paul, Aditya Kusupati

24 upvotesApril 10, 2026arXiv 预印本
AI 摘要

Elastic Looped Transformers utilize recurrent transformer architecture with weight-sharing and intra-loop self-distillation to achieve parameter-efficient visual generation with adjustable computational cost and generation quality.

recurrent transformer architectureweight-sharingparameter-efficientvisual generative modelsIntra-Loop Self Distillationstudent configurationsteacher configurationAny-Time inferenceFIDFVD

Abstract

We introduce Elastic Looped Transformers (ELT), a highly parameter-efficient class of visual generative models based on a recurrent transformer architecture. While conventional generative models rely on deep stacks of unique transformer layers, our approach employs iterative, weight-shared transformer blocks to drastically reduce parameter counts while maintaining high synthesis quality. To effectively train these models for image and video generation, we propose the idea of Intra-Loop Self Distillation (ILSD), where student configurations (intermediate loops) are distilled from the teacher configuration (maximum training loops) to ensure consistency across the model's depth in a single training step. Our framework yields a family of elastic models from a single training run, enabling Any-Time inference capability with dynamic trade-offs between computational cost and generation quality, with the same parameter count. ELT significantly shifts the efficiency frontier for visual synthesis. With 4times reduction in parameter count under iso-inference-compute settings, ELT achieves a competitive FID of 2.0 on class-conditional ImageNet 256 times 256 and FVD of 72.8 on class-conditional UCF-101.

北京市昌平区探索星信息技术及软件开发工作室

京ICP备2026059466号