analiza aiqbench
This research proposes FMSGOC, a framework leveraging vision-language foundation models and diffusion priors to achieve efficient semantic communication at extremely low bit rates. By transmitting only sparse semantic anchors rather than full signals, the system significantly improves generalization on unseen data compared to traditional compression methods. This approach directly addresses critical bottlenecks in 6G networks where bandwidth is constrained but high-fidelity understanding remains essential.
Foundation Models for Generalizable Semantic and Goal-Oriented Communication
arXiv:2609.07853v1 Announce Type: new Abstract: Semantic and goal-oriented communication is increasingly studied for 6G, but generalization beyond seen data remains a key weakness under tight rate budgets. Many existing systems overfit their training data and degrade sharply at very low bit rates because they attempt to compress the entire signal. We introduce Foundation Model-Guided Semantic and Goal-Oriented Communication (FMSGOC), a framework that uses broad visual-linguistic Foundation Model priors to mitigate overfitting. It further improves rate efficiency by concentrating bits on sparse, goal-aligned anchors and relying on generative foundation-model priors to reconstruct the masked regions. By decoupling what to send from how to reconstruct, a vision-language foundation model selects and transmits a sparse set of semantic anchors, while a pretrained diffusion model, fine-tuned for masked completion, reconstructs the image at the receiver. In our experiments, FMSGOC reaches 0.039 bits per pixel (BPP), maintains high semantic fidelity (cosine similarity 0.87-0.90 on CIFAR-10), remains robust on previously unseen inputs (0.83-0.86 on ImageNet), and shows good perceptual similarity (0.1278/0.1558, CIFAR-10/ImageNet), outperforming strong end-to-end baselines at lower bit rates.
Abstract:Semantic and goal-oriented communication is increasingly studied for 6G, but generalization beyond seen data remains a key weakness under tight rate budgets. Many existing systems overfit their training data and degrade sharply at very low bit rates because they attempt to compress the entire signal. We introduce Foundation Model-Guided Semantic and Goal-Oriented Communication (FMSGOC), a framework that uses broad visual-linguistic Foundation Model priors to mitigate overfitting. It further improves rate efficiency by concentrating bits on sparse, goal-aligned anchors and relying on generative foundation-model priors to reconstruct the masked regions. By decoupling what to send from how to reconstruct, a vision-language foundation model selects and transmits a sparse set of semantic anchors, while a pretrained diffusion model, fine-tuned for masked completion, reconstructs the image at the receiver. In our experiments, FMSGOC reaches 0.039 bits per pixel (BPP), maintains high semantic fidelity (cosine similarity 0.87-0.90 on CIFAR-10), remains robust on previously unseen inputs (0.83-0.86 on ImageNet), and shows good perceptual similarity (0.1278/0.1558, CIFAR-10/ImageNet), outperforming strong end-to-end baselines at lower bit rates.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Robotics (cs.RO); Image and Video Processing (eess.IV)
arXiv:2609.07853 [cs.LG]
(or arXiv:2609.07853v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.07853 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
2026 IEEE International Conference on Communications (ICC), pp. 1-6, 2026
https://doi.org/10.1109/ICC59461.2026.11588119 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 293 cuvinte
Subiecte conexe
Presentation: Designing AI Platforms for Reliability: Tools for Certainty, Agents for Discovery
InfoQ · 27 mai 2026
State of the Field: AI for Epistemics and Coordination
LessWrong · 2 oct. 2026
How to Use AI Agents to Prepare 3D Scenes for Simulation
NVIDIA · 16 sept. 2026
Game Design Creativity evals
LessWrong · 12 oct. 2026