paper-with-me

Papers

TAG-MoE: Task-Aware Gating for Unified Generative Mixture-of-Experts

2026-01-12 · Yu Xu, Hongbin Yan, Juan Cao, Yiji Cheng, Tiankai Hang, Runze He, Zijin Yin, Shiyi Zhang, Yuxin Zhang, Jintao Li, Chunyu Wang, Qinglin Lu, Tong-Yee Lee, Fan Tang arxiv

Unified image generation and editing models suffer from severe task interference in dense diffusion transformers architectures, where a shared parameter space must compromise between conflicting objectives (e.g., local editing v.s. subject-driven generation). While the sparse Mixture-of-Experts (MoE) paradigm is a promising solution, its gating networks remain task-agnostic, operating based on local features, unaware of global task intent. This task-agnostic nature prevents meaningful specialization and fails to resolve the underlying task interference. In this paper, we propose a novel framework to inject semantic intent into MoE routing. We introduce a Hierarchical Task Semantic Annotation scheme to create structured task descriptors (e.g., scope, type, preservation). We then design Predictive Alignment Regularization to align internal routing decisions with the task's high-level semantics. This regularization evolves the gating network from a task-agnostic executor to a dispatch center. Our model effectively mitigates task interference, outperforming dense baselines in fidelity and quality, and our analysis shows that experts naturally develop clear and semantically correlated specializations.

📄 PDF Abstract BibTeX arXiv:2601.08881

Code (0)

등록된 구현이 없습니다.

Tasks

Image Generation

Similar Papers 제목 키워드 기반

TrueMoE: Dual-Routing Mixture of Discriminative Experts for Synthetic Image Detection

2025-09-19 · Laixin Zhang, Shuaibo Li, Wei Ma, Hongbin Zha arxiv

The rapid progress of generative models has made synthetic image detection an increasingly critical task. Most existing approaches attempt to construct a single, universal discriminative space to separate real from fake …

Drift-Aware Multimodal User Representation Learning via Multi-Scale Temporal Modeling and Sparse Mixture-of-Experts

2026-08-26 · Ziqing Qian, Haohang Chen, Shengqi Dang, Yuhan Xiong 외 arxiv

Understanding user preferences from noisy and temporally evolving social media behaviors is fundamentally challenging due to interest drift, where user preferences shift across time and exhibit both multi-scale temporal …

Representation Learning

Towards a Unified Generative Model for Scarce Time Series with Domain Experts

2026-06-13 · Zihao Yao, Qi Zheng, Jiankai Zuo, Yaying Zhang arxiv

Synthesizing realistic time series with generative models has wide-ranging applications in real-world scenarios. Despite recent progress, most existing methods are trained under the assumption of abundant training data, …

From Moments to Models: Graphon-Mixture Learning for Mixup and Contrastive Learning

2025-10-04 · Ali Azizpour, Reza Ramezanpour, Santiago Segarra arxiv

Real-world graph datasets often arise from mixtures of populations, where graphs are generated by multiple distinct underlying distributions. In this work, we propose a unified framework that explicitly models graph data…

Contrastive LearningData Augmentation

Multi-Task Vehicle Routing Solver via Mixture of Specialized Experts under State-Decomposable MDP

2025-10-24 · Yuxin Pan, Zhiguang Cao, Chengyang Gu, Liu Liu 외 arxiv

Existing neural methods for multi-task vehicle routing problems (VRPs) typically learn unified solvers to handle multiple constraints simultaneously. However, they often underutilize the compositional structure of VRP va…