Cover Image

Optimus-3: Dual-Router Aligned Mixture-of-Experts Agent with Dual-Granularity Reasoning-Aware Policy Optimization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Zaijing, Xie, Yuquan, Shao, Rui, Chen, Gongwei, Guan, Weili, Jiang, Dongmei, Wang, Yaowei, Nie, Liqiang
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Optimus-2: Multimodal Minecraft Agent with Goal-Observation-Action Conditioned Policy
by: Li, Zaijing, et al.
Published: (2025)

Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks
by: Li, Zaijing, et al.
Published: (2024)

Enhancing Emotional Generation Capability of Large Language Models via Emotional Chain-of-Thought
by: Li, Zaijing, et al.
Published: (2024)

Mirage-1: Augmenting and Updating GUI Agent with Hierarchical Multimodal Skills
by: Xie, Yuquan, et al.
Published: (2025)

MoME: Mixture of Multimodal Experts for Generalist Multimodal Large Language Models
by: Shen, Leyang, et al.
Published: (2024)

Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulation
by: Li, Zaijing, et al.
Published: (2026)

PersonalAlign: Hierarchical Implicit Intent Alignment for Personalized GUI Agent with Long-Term User-Centric Records
by: Lyu, Yibo, et al.
Published: (2026)

DAgger Diffusion Navigation: DAgger Boosted Diffusion Policy for Vision-Language Navigation
by: Shi, Haoxiang, et al.
Published: (2025)

HiconAgent: History Context-aware Policy Optimization for GUI Agents
by: Zhou, Xurui, et al.
Published: (2025)

Spatial Understanding from Videos: Structured Prompts Meet Simulation Data
by: Zhang, Haoyu, et al.
Published: (2025)

PUMA: Layer-Pruned Language Model for Efficient Unified Multimodal Retrieval with Modality-Adaptive Learning
by: Lyu, Yibo, et al.
Published: (2025)

Token-level Correlation-guided Compression for Efficient Multimodal Document Understanding
by: Zhang, Renshan, et al.
Published: (2024)

Curriculum Coarse-to-Fine Selection for High-IPC Dataset Distillation
by: Chen, Yanda, et al.
Published: (2025)

FALCON: Resolving Visual Redundancy and Fragmentation in High-resolution Multimodal Large Language Models via Visual Registers
by: Zhang, Renshan, et al.
Published: (2025)

HCQA @ Ego4D EgoSchema Challenge 2024
by: Zhang, Haoyu, et al.
Published: (2024)

ObjectNLQ @ Ego4D Episodic Memory Challenge 2024
by: Feng, Yisen, et al.
Published: (2024)

Dual Knowledge-Enhanced Two-Stage Reasoner for Multimodal Dialog Systems
by: Chen, Xiaolin, et al.
Published: (2025)

HATS: Hardness-Aware Trajectory Synthesis for GUI Agents
by: Shao, Rui, et al.
Published: (2026)

Uncovering Hidden Connections: Iterative Search and Reasoning for Video-grounded Dialog
by: Zhang, Haoyu, et al.
Published: (2023)

Mixture-of-Schedulers: An Adaptive Scheduling Agent as a Learned Router for Expert Policies
by: Wang, Xinbo, et al.
Published: (2025)

Router Upcycling: Leveraging Mixture-of-Routers in Mixture-of-Experts Upcycling
by: Ran, Junfeng, et al.
Published: (2025)

EnergyAction: Unimanual to Bimanual Composition with Energy-Based Models
by: Song, Mingchen, et al.
Published: (2026)

DeepFake-Adapter: Dual-Level Adapter for DeepFake Detection
by: Shao, Rui, et al.
Published: (2023)

GUI-explorer: Autonomous Exploration and Mining of Transition-aware Knowledge for GUI Agent
by: Xie, Bin, et al.
Published: (2025)

Less is More: Empowering GUI Agent with Context-Aware Simplification
by: Chen, Gongwei, et al.
Published: (2025)

Beyond Quantity: Distribution-Aware Labeling for Visual Grounding
by: Zhang, Yichi, et al.
Published: (2025)

Layerwise Recurrent Router for Mixture-of-Experts
by: Qiu, Zihan, et al.
Published: (2024)

StructAlign: Structured Cross-Modal Alignment for Continual Text-to-Video Retrieval
by: Wang, Shaokun, et al.
Published: (2026)

JFAA: Technical Report for the EPIC-KITCHENS-100 Action Anticipation Challenge at EgoVis 2026
by: Chu, Qiaohui, et al.
Published: (2026)

VISTA: Technical Report for the Ego4D Short-Term Object Interaction Anticipation at EgoVis 2026
by: Chu, Qiaohui, et al.
Published: (2026)

MARS: Technical Report for the CASTLE Challenge at EgoVis 2026
by: Zhang, Haoyu, et al.
Published: (2026)

OSGNet @ Ego4D Episodic Memory Challenge 2025
by: Feng, Yisen, et al.
Published: (2025)

Technical Report for Ego4D Long-Term Action Anticipation Challenge 2025
by: Chu, Qiaohui, et al.
Published: (2025)

HCQA-1.5 @ Ego4D EgoSchema Challenge 2025
by: Zhang, Haoyu, et al.
Published: (2025)

Routers in Vision Mixture of Experts: An Empirical Study
by: Liu, Tianlin, et al.
Published: (2024)

RouterKT: Mixture-of-Experts for Knowledge Tracing
by: Liao, Han, et al.
Published: (2025)

Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss
by: Lv, Ang, et al.
Published: (2025)

Long-Tailed Distribution-Aware Router For Mixture-of-Experts in Large Vision-Language Model
by: Cai, Chaoxiang, et al.
Published: (2025)

Load Balancing Mixture of Experts with Similarity Preserving Routers
by: Omi, Nabil, et al.
Published: (2025)

Statistical Advantages of Perturbing Cosine Router in Mixture of Experts
by: Nguyen, Huy, et al.
Published: (2024)