PRISM — Photonic Recursive Intelligence with Synaptic Memory · Coherent IQ fiber neural network · Recursive meta-prompt · 4 telecom classifiers at 100% accuracy · IIT Mandi · Himshikhar 2026
-
Updated
May 27, 2026 - Python
PRISM — Photonic Recursive Intelligence with Synaptic Memory · Coherent IQ fiber neural network · Recursive meta-prompt · 4 telecom classifiers at 100% accuracy · IIT Mandi · Himshikhar 2026
Knowledge Graph-Enhanced LoRA Fine-Tuning for Intelligent 3GPP-Compliant 5G Network Slicing. Maps raw 5G telemetry to 3GPP standards using SVO triples and fine-tuned Llama-3.2-1B models.
Agentic AI-driven framework for 3GPP-compliant (TS 23.501) resource allocation in 5G NR Satellite Networks. Integrates ML models as tools for a LangChain ReAct agent.
Colosseum-based O-RAN slice resource allocation via Federated Learning & Differential Privacy (Opacus). ClusteredFL · FedProx · DQN · PyTorch
Agentic-RAN is a reproducible PyTorch benchmark for comparing neural-network architectures on RAN-oriented regression and sequence-prediction tasks, including MLP, attention, liquid-dynamics, and xLSTM scenarios. It provides Docker-based execution, standardized evaluation metrics, prediction plots, and automated benchmark reports.
Add a description, image, and links to the telecom-ai topic page so that developers can more easily learn about it.
To associate your repository with the telecom-ai topic, visit your repo's landing page and select "manage topics."