LPSE uses latent predictive learning on permutation-invariant node representations to deliver 82.42% semantic accuracy at 41x lower latency and 15x smaller memory than a 4B LLM while generalizing to changing node sets without retraining.
Multi- agentic ai for fairness-aware and accelerated multi-modal large model inference in real-world mobile edge networks,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Low-Latency Semantic State Estimator using Latent Predictive Learning for Dynamic Network Monitoring and Orchestration
LPSE uses latent predictive learning on permutation-invariant node representations to deliver 82.42% semantic accuracy at 41x lower latency and 15x smaller memory than a 4B LLM while generalizing to changing node sets without retraining.