Imagen de Portada

DeepOmni: Towards Seamless and Smart Speech Interaction with Adaptive Modality-Specific MoE

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Shao, Hang, Gao, Heting, Shen, Yunhang, Chen, Jiawei, Long, Zuwei, Yang, Dong, Li, Ke, Sun, Xing
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion
por: Li, Lijiang, et al.
Publicado: (2026)

VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model
por: Long, Zuwei, et al.
Publicado: (2025)

Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM
por: Wang, Xiong, et al.
Publicado: (2024)

VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction
por: Fu, Chaoyou, et al.
Publicado: (2025)

VITA: Towards Open-Source Interactive Omni Multimodal LLM
por: Fu, Chaoyou, et al.
Publicado: (2024)

LUCY: Linguistic Understanding and Control Yielding Early Stage of Her
por: Gao, Heting, et al.
Publicado: (2025)

OmniCharacter: Towards Immersive Role-Playing Agents with Seamless Speech-Language Personality Interaction
por: Zhang, Haonan, et al.
Publicado: (2025)

LLaMA-Omni: Seamless Speech Interaction with Large Language Models
por: Fang, Qingkai, et al.
Publicado: (2024)

MoE-Hub: Taming Software Complexity for Seamless MoE Overlap with Hardware-Accelerated Communication on Multi-GPU Systems
por: Zhou, Zhuoshan, et al.
Publicado: (2026)

OmniMoE: An Efficient MoE by Orchestrating Atomic Experts at Scale
por: Shi, Jingze, et al.
Publicado: (2026)

VEQ: Modality-Adaptive Quantization for MoE Vision-Language Models
por: Qin, Guangshuo, et al.
Publicado: (2026)

Omni-Referring Image Segmentation
por: Zheng, Qiancheng, et al.
Publicado: (2025)

GW-MoE: Resolving Uncertainty in MoE Router with Global Workspace Theory
por: Wu, Haoze, et al.
Publicado: (2024)

Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data
por: Li, Yunxin, et al.
Publicado: (2025)

OmniGAIA: Towards Native Omni-Modal AI Agents
por: Li, Xiaoxi, et al.
Publicado: (2026)

Grove MoE: Towards Efficient and Superior MoE LLMs with Adjugate Experts
por: Wu, Haoyuan, et al.
Publicado: (2025)

FlexiReID: Adaptive Mixture of Expert for Multi-Modal Person Re-Identification
por: Sun, Zhen, et al.
Publicado: (2025)

SMoES: Soft Modality-Guided Expert Specialization in MoE-VLMs
por: Bo, Zi-Hao, et al.
Publicado: (2026)

MiM-DiT: MoE in MoE with Diffusion Transformers for All-in-One Image Restoration
por: Kong, Lingshun, et al.
Publicado: (2026)

MoTAS: MoE-Guided Feature Selection from TTS-Augmented Speech for Enhanced Multimodal Alzheimer's Early Screening
por: Shao, Yongqi, et al.
Publicado: (2025)

MoE3D: Mixture of Experts meets Multi-Modal 3D Understanding
por: Li, Yu, et al.
Publicado: (2025)

EVE: Efficient Vision-Language Pre-training with Masked Prediction and Modality-Aware MoE
por: Chen, Junyi, et al.
Publicado: (2023)

Flex-MoE: Modeling Arbitrary Modality Combination via the Flexible Mixture-of-Experts
por: Yun, Sukwon, et al.
Publicado: (2024)

Is Extending Modality The Right Path Towards Omni-Modality?
por: Zhu, Tinghui, et al.
Publicado: (2025)

Towards Unsupervised Speech Recognition Without Pronunciation Models
por: Ni, Junrui, et al.
Publicado: (2024)

InterMoE: Individual-Specific 3D Human Interaction Generation via Dynamic Temporal-Selective MoE
por: Wang, Lipeng, et al.
Publicado: (2025)

MoE-Loco: Mixture of Experts for Multitask Locomotion
por: Huang, Runhan, et al.
Publicado: (2025)

MinMo: A Multimodal Large Language Model for Seamless Voice Interaction
por: Chen, Qian, et al.
Publicado: (2025)

Omni-DeepSearch: A Benchmark for Audio-Driven Omni-Modal Deep Search
por: Yu, Tao, et al.
Publicado: (2026)

BIG-MoE: Bypass Isolated Gating MoE for Generalized Multimodal Face Anti-Spoofing
por: Ma, Yingjie, et al.
Publicado: (2024)

KBVQ-MoE: KLT-guided SVD with Bias-Corrected Vector Quantization for MoE Large Language Models
por: Xu, Zukang, et al.
Publicado: (2026)

I2MoE: Interpretable Multimodal Interaction-aware Mixture-of-Experts
por: Xin, Jiayi, et al.
Publicado: (2025)

AST: Adaptive, Seamless, and Training-Free Precise Speech Editing
por: Lv, Sihan, et al.
Publicado: (2026)

Mix-MoE: Improving Multilingual Machine Translation of Large Language Models through Mixed MoEs
por: Li, Bo, et al.
Publicado: (2026)

OmniJigsaw: Enhancing Omni-Modal Reasoning via Modality-Orchestrated Reordering
por: Jia, Yiduo, et al.
Publicado: (2026)

VA-MoE: Variables-Adaptive Mixture of Experts for Incremental Weather Forecasting
por: Chen, Hao, et al.
Publicado: (2024)

iSchools and Non-iSchools in the USA: An Examination of Their Master's Programs
por: Chu, Heting
Publicado: (2012)

Hyperlinks: How Well Do They Represent the Intellectual Content of Digital Collections?
por: Chu, Heting
Publicado: (1997)

ExpertFlow: Adaptive Expert Scheduling and Memory Coordination for Efficient MoE Inference
por: Shen, Zixu, et al.
Publicado: (2025)

MoE-Lens: Towards the Hardware Limit of High-Throughput MoE LLM Serving Under Resource Constraints
por: Yuan, Yichao, et al.
Publicado: (2025)