Foundation Models for Generalizable Semantic and Goal-Oriented Communication
FMSGOC uses vision-language foundation model priors plus diffusion reconstruction to enable generalizable semantic communication at 0.039 bits per pixel for 6G.
FMSGOC targets generalization failures in semantic and goal-oriented communication for 6G by leveraging broad visual-linguistic foundation model priors. A vision-language model selects sparse, goal-aligned semantic anchors while a fine-tuned diffusion model performs masked completion to reconstruct images at the receiver, decoupling what to send from how to reconstruct. On CIFAR-10 it reaches 0.039 bits per pixel with cosine similarity 0.87-0.90 and 0.83-0.86 on unseen ImageNet inputs, outperforming end-to-end baselines at lower bit rates.
- Decouples anchor selection (VLM) from masked-completion reconstruction (diffusion) for rate efficiency
- 0.039 BPP with cosine similarity 0.87-0.90 on CIFAR-10, 0.83-0.86 on unseen ImageNet
- Aims to fix overfitting and sharp degradation of prior systems at very low bit rates
- Tags
- 6gdiffusion-modelsfoundation-modelsgoal-oriented-communicationimage-compressionsemantic-communicationvision-language
- AI models
- FMSGOC
From the original article
1 min read at arxiv.orgSemantic 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.
By Boliang Liu · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.