Cover Image

Mixture of States: Routing Token-Level Dynamics for Multimodal Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Haozhe, Liu, Ding, Zhuge, Mingchen, Zhou, Zijian, Xie, Tian, He, Sen, Yang, Yukang, Liu, Shuming, Cong, Yuren, Guo, Jiadong, Xu, Hongyu, Xu, Ke, Ng, Kam-Woh, Pérez, Juan C., Pérez-Rúa, Juan-Manuel, Xiang, Tao, Liu, Wei, Liu, Shikun, Schmidhuber, Jürgen
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Learning Flow Fields in Attention for Controllable Person Image Generation
by: Zhou, Zijian, et al.
Published: (2024)

Scaling Sequence-to-Sequence Generative Neural Rendering
by: Liu, Shikun, et al.
Published: (2025)

Rays as Pixels: Learning A Joint Distribution of Videos and Camera Trajectories
by: Jang, Wonbong, et al.
Published: (2026)

Scaling Zero-Shot Reference-to-Video Generation
by: Zhou, Zijian, et al.
Published: (2025)

MarDini: Masked Autoregressive Diffusion for Video Generation at Scale
by: Liu, Haozhe, et al.
Published: (2024)

HiStream: Efficient High-Resolution Video Generation via Redundancy-Eliminated Streaming
by: Qiu, Haonan, et al.
Published: (2025)

Faster Diffusion via Temporal Attention Decomposition
by: Liu, Haozhe, et al.
Published: (2024)

TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models
by: Liu, Zhiheng, et al.
Published: (2025)

Beyond Outlining: Heterogeneous Recursive Planning for Adaptive Long-form Writing with Language Models
by: Xiong, Ruibin, et al.
Published: (2025)

Neural Computers
by: Zhuge, Mingchen, et al.
Published: (2026)

ConceptHash: Interpretable Fine-Grained Hashing via Concept Discovery
by: Ng, Kam Woh, et al.
Published: (2024)

PartCraft: Crafting Creative Objects by Parts
by: Ng, Kam Woh, et al.
Published: (2024)

Language Agents as Optimizable Graphs
by: Zhuge, Mingchen, et al.
Published: (2024)

VecGlypher: Unified Vector Glyph Generation with Language Models
by: Huang, Xiaoke, et al.
Published: (2026)

GenTron: Diffusion Transformers for Image and Video Generation
by: Chen, Shoufa, et al.
Published: (2023)

FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing
by: Cong, Yuren, et al.
Published: (2023)

Lazy Layers to Make Fine-Tuned Diffusion Models More Traceable
by: Liu, Haozhe, et al.
Published: (2024)

TROPHIES: Temporal Reconstruction of Places, Humans, and Cameras from Multi-view Videos
by: Liu, Jinpeng, et al.
Published: (2026)

Mixture of Sparse Attention: Content-Based Learnable Sparse Attention via Expert-Choice Routing
by: Piękos, Piotr, et al.
Published: (2025)

No Clustering, No Routing: How Transformers Actually Process Rare Tokens
by: Liu, Jing
Published: (2025)

VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice
by: Liu, Shuming, et al.
Published: (2026)

TradExpert: Revolutionizing Trading with Mixture of Expert LLMs
by: Ding, Qianggang, et al.
Published: (2024)

MC#: Mixture Compressor for Mixture-of-Experts Large Models
by: Huang, Wei, et al.
Published: (2025)

Routing-Free Mixture-of-Experts
by: Liu, Yilun, et al.
Published: (2026)

IPR-NeRF: Ownership Verification meets Neural Radiance Field
by: Ong, Win Kent, et al.
Published: (2024)

Huxley-Gödel Machine: Human-Level Coding Agent Development by an Approximation of the Optimal Self-Improving Machine
by: Wang, Wenyi, et al.
Published: (2025)

Token-Budget-Aware Pool Routing for Cost-Efficient LLM Inference
by: Chen, Huamin, et al.
Published: (2026)

Memory Efficient Matting with Adaptive Token Routing
by: Lin, Yiheng, et al.
Published: (2024)

Proof of a conjecture of Garvan and Jennings-Shaffer on the nonnegativity of M_{C1}(m,n) and M_{C5}(m,n)
by: He, Bing, et al.
Published: (2025)

Weighted partial sums of a random multiplicative function and their positivity
by: Liu, Shuming, et al.
Published: (2025)

The boundary of Kirkwood-Dirac quasiprobability
by: Liu, Lijun, et al.
Published: (2025)

Towards Cost-effective LLMs Routing with Batch Prompting
by: Xu, Haotian, et al.
Published: (2026)

Mixture of Heterogeneous Grouped Experts for Language Modeling
by: Ma, Zhicheng, et al.
Published: (2026)

CrowdMoGen: Zero-Shot Text-Driven Collective Motion Generation
by: Cao, Yukang, et al.
Published: (2024)

Hyper-VolTran: Fast and Generalizable One-Shot Image to 3D Object Structure via HyperNetworks
by: Simon, Christian, et al.
Published: (2023)

Determining a nonlinear hyperbolic system with unknown sources and nonlinearity
by: Yi‐Hsuan Lin, et al.
Published: (2024)

Learning with Semantics: Towards a Semantics-Aware Routing Anomaly Detection System
by: Chen, Yihao, et al.
Published: (2024)

Linear Mixture Distributionally Robust Markov Decision Processes
by: Liu, Zhishuai, et al.
Published: (2025)

BOLT: Boost Large Vision-Language Model Without Training for Long-form Video Understanding
by: Liu, Shuming, et al.
Published: (2025)

Dual-Pool Token-Budget Routing for Cost-Efficient and Reliable LLM Serving
by: Liu, Xunzhuo, et al.
Published: (2026)