paper-with-me

Papers

Dynamic Mixture-of-Experts for Visual Autoregressive Model

2025-10-08 · Jort Vincenti, Metod Jazbec, Guoxuan Xia arxiv

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.

📄 PDF Abstract BibTeX arXiv:2510.08629

Code (0)

등록된 구현이 없습니다.

Tasks

Image Generation

Similar Papers 제목 키워드 기반

Imitation Learning from Observations: An Autoregressive Mixture of Experts Approach

2024-11-12 · Renzi Wang, Flavia Sofia Acerbo, Tong Duy Son, Panagiotis Patrinos

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-Experts

LongScape: Advancing Long-Horizon Embodied World Models with Context-Aware MoE

2025-09-26 · Yu Shang, Lei Jin, Yiding Ma, Xin Zhang 외 arxiv

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 Generation

MEPA: Multi-Scale Representation Alignment for Visual Autoregressive Modeling with Mixture of Experts

2026-07-01 · Nuoyan Zhou, Zhijun Tu, Lei Yu, Kun Cheng 외 arxiv

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 Generation

ATG-MoE: Autoregressive trajectory generation with mixture-of-experts for assembly skill learning

2026-03-19 · Weihang Huang, Chaoran Zhang, Xiaoxin Deng, Hao Zhou 외 arxiv

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

2026-03-12 · Hanchi Sun, Yixin Liu, Yonghui Wu, Lichao Sun arxiv

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…