Dynamic Mixture-of-Experts for Visual Autoregressive Model
Visual Autoregressive Models (VAR) offer efficient and high-quality image generation but suffer from computational redundancy due to repeated Transformer calls at increasing resolutions. We introduce a dynamic Mixture-of-Experts router integrated into VAR. The new architecture allows to trade compute for quality through scale-aware thresholding. This thresholding strategy balances expert selection based on token complexity and resolution, without requiring additional training. As a result, we achieve 20% fewer FLOPs, 11% faster inference and match the image quality achieved by the dense baseline.
Code (0)
등록된 구현이 없습니다.
Tasks
Image GenerationSimilar Papers 제목 키워드 기반
Imitation Learning from Observations: An Autoregressive Mixture of Experts Approach
This paper presents a novel approach to imitation learning from observations, where an autoregressive mixture of experts model is deployed to fit the underlying policy. The parameters of the model are learned via a two-s…
Autonomous DrivingImitation LearningMixture-of-ExpertsLongScape: Advancing Long-Horizon Embodied World Models with Context-Aware MoE
Video-based world models hold significant potential for generating high-quality embodied manipulation data. However, current video generation methods struggle to achieve stable long-horizon generation: classical diffusio…
Video GenerationMEPA: Multi-Scale Representation Alignment for Visual Autoregressive Modeling with Mixture of Experts
Visual AutoRegressive modeling (VAR) has pioneered a coarse-to-fine multi-scale autoregressive generative paradigm, demonstrating strong capabilities in image generation. However, VAR still suffers from inherent deficien…
Representation LearningImage GenerationATG-MoE: Autoregressive trajectory generation with mixture-of-experts for assembly skill learning
Flexible manufacturing requires robot systems that can adapt to constantly changing tasks, objects, and environments. However, traditional robot programming is labor-intensive and inflexible, while existing learning-base…
Expert Threshold Routing for Autoregressive Language Modeling with Dynamic Computation Allocation and Load Balancing
Token-choice Mixture-of-Experts (TC-MoE) routes each token to a fixed number of experts, limiting dynamic computation allocation and requiring auxiliary losses to maintain load balance. We propose Expert Threshold (ET) r…