Copertina

The Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systems

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Liu, Xiaoze, Zhang, Ruowang, Yu, Weichen, Xiong, Siheng, He, Liu, Wu, Feijie, Jung, Hoin, Fredrikson, Matt, Wang, Xiaoqian, Gao, Jing
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language Computer Vision and Pattern Recognition Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

When the Same Coefficients Reach Different Places: Asymmetric Realizability in Transplanting Tokenizers across Large Language Models
di: Liu, Xiaoze, et al.
Pubblicazione: (2025)

Do Proactive Agents Really Need an LLM to Decide When to Wake and What to Anchor?
di: Liu, Xiaoze, et al.
Pubblicazione: (2026)

SUV: Scalable Large Language Model Copyright Compliance with Regularized Selective Unlearning
di: Xu, Tianyang, et al.
Pubblicazione: (2025)

The Cost of Context: Mitigating Textual Bias in Multimodal Retrieval-Augmented Generation
di: Jung, Hoin, et al.
Pubblicazione: (2026)

A Unified Debiasing Approach for Vision-Language Models across Modalities and Tasks
di: Jung, Hoin, et al.
Pubblicazione: (2024)

SHIELD: Evaluation and Defense Strategies for Copyright Compliance in LLM Text Generation
di: Liu, Xiaoze, et al.
Pubblicazione: (2024)

Evaluating the Factuality of Large Language Models using Large-Scale Knowledge Graphs
di: Liu, Xiaoze, et al.
Pubblicazione: (2024)

Towards Federated RLHF with Aggregated Client Preference for LLMs
di: Wu, Feijie, et al.
Pubblicazione: (2024)

Transferable Adversarial Attacks on Black-Box Vision-Language Models
di: Hu, Kai, et al.
Pubblicazione: (2025)

X-MAS: Towards Building Multi-Agent Systems with Heterogeneous LLMs
di: Ye, Rui, et al.
Pubblicazione: (2025)

FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extraction
di: Wu, Feijie, et al.
Pubblicazione: (2024)

Talk to Right Specialists: Iterative Routing in Multi-agent Systems for Question Answering
di: Wu, Feijie, et al.
Pubblicazione: (2025)

Linking Modality Isolation in Heterogeneous Collaborative Perception
di: Liu, Changxing, et al.
Pubblicazione: (2026)

CausalEval: Towards Better Causal Reasoning in Language Models
di: Yu, Longxuan, et al.
Pubblicazione: (2024)

Is Your Text-to-Image Model Robust to Caption Noise?
di: Yu, Weichen, et al.
Pubblicazione: (2024)

Communication-Efficient Multi-Agent 3D Detection via Hybrid Collaboration
di: Hu, Yue, et al.
Pubblicazione: (2025)

Towards Long-horizon Embodied Agents with Tool-Aligned Vision-Language-Action Models
di: Lei, Zixing, et al.
Pubblicazione: (2026)

FedBiOT: LLM Local Fine-tuning in Federated Learning without Full Model
di: Wu, Feijie, et al.
Pubblicazione: (2024)

Enhancing Long Chain-of-Thought Reasoning through Multi-Path Plan Aggregation
di: Xiong, Siheng, et al.
Pubblicazione: (2025)

Pragmatic Communication in Multi-Agent Collaborative Perception
di: Hu, Yue, et al.
Pubblicazione: (2024)

Reasoning Path and Latent State Analysis for Multi-view Visual Spatial Reasoning: A Cognitive Science Perspective
di: Xue, Qiyao, et al.
Pubblicazione: (2025)

MAS-GPT: Training LLMs to Build LLM-based Multi-Agent Systems
di: Ye, Rui, et al.
Pubblicazione: (2025)

Coherence-Aware Task Graph Modeling for Realistic Application
di: Xiong, Guochu, et al.
Pubblicazione: (2025)

LatentMem: Customizing Latent Memory for Multi-Agent Systems
di: Fu, Muxin, et al.
Pubblicazione: (2026)

Latent Collaboration in Multi-Agent Systems
di: Zou, Jiaru, et al.
Pubblicazione: (2025)

HyLaT: Efficient Multi-Agent Communication via Hybrid Latent-Text Protocol
di: Mou, Xinyi, et al.
Pubblicazione: (2026)

MosaicThinker: On-Device Visual Spatial Reasoning for Embodied AI via Iterative Construction of Space Representation
di: Wang, Haoming, et al.
Pubblicazione: (2026)

Deliberate Planning in Language Models with Symbolic Representation
di: Xiong, Siheng, et al.
Pubblicazione: (2025)

Exploring Deep-to-Shallow Transformable Neural Networks for Intelligent Embedded Systems
di: Luo, Xiangzhong, et al.
Pubblicazione: (2025)

Experience Sharing in Mutual Reinforcement Learning for Heterogeneous Language Models
di: Liu, Xiaoze, et al.
Pubblicazione: (2026)

$λ$-ECLIPSE: Multi-Concept Personalized Text-to-Image Diffusion Models by Leveraging CLIP Latent Space
di: Patel, Maitreya, et al.
Pubblicazione: (2024)

Verifiable Cloud‐Assisted Multi‐Party Private Set Intersection Cardinality
di: Gongli Li, et al.
Pubblicazione: (2025)

Automated Sentiment Classification and Topic Discovery in Large-Scale Social Media Streams
di: Lu, Yiwen, et al.
Pubblicazione: (2025)

HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning
di: Wang, Shenzhi, et al.
Pubblicazione: (2026)

PORTool: Importance-Aware Policy Optimization with Rewarded Tree for Multi-Tool-Integrated Reasoning
di: Wu, Feijie, et al.
Pubblicazione: (2025)

Rate-Distortion Optimized Communication for Collaborative Perception
di: Liu, Genjia, et al.
Pubblicazione: (2025)

Reasoning in the Dark: Interleaved Vision-Text Reasoning in Latent Space
di: Chen, Chao, et al.
Pubblicazione: (2025)

System-1.5 Reasoning: Traversal in Language and Latent Spaces with Dynamic Shortcuts
di: Wang, Xiaoqiang, et al.
Pubblicazione: (2025)

Progressive Modality Cooperation for Multi-Modality Domain Adaptation
di: Zhang, Weichen, et al.
Pubblicazione: (2025)

Adaptive Vision-Language Model Routing for Computer Use Agents
di: Liu, Xunzhuo, et al.
Pubblicazione: (2026)