4 papers
A Picture is Worth a Thousand Tokens: How Vision Language Models Cut AI Energy Costs While Improving Accuracy
Bhavika Jalli, Nikhil Korati Prasanna, Jayanta Choudhury
LLM inference accounts for over 90% of AI operational energy, scaling directly with input token count---a critical inefficiency for telecom network analytics and numerical time-ser…
Leveraging Multi-Agent System (MAS) and Fine-Tuned Small Language Models (SLMs) for Automated Telecom Network Troubleshooting
Chenhua Shi, Bhavika Jalli, Gregor Macdonald +4
Telecom networks are rapidly growing in scale and complexity, making effective management, operation, and optimization increasingly challenging. Although Artificial Intelligence (A…
Edge-Deployable LLM Fine-Tuning on a Single GPU for Telecom Network Troubleshooting
Chenhua Shi, Bhavika Jalli, John Zou +4
Telecom troubleshooting at edge sites requires low-latency model responses and localized model adaptation to satisfy operational and data sovereignty requirements. However, deployi…
Think Less, Label Better: Multi-Stage Domain-Grounded Synthetic Data Generation for Fine-Tuning Large Language Models in Telecommunications
Chenhua Shi, Gregor Macdonald, Bhavika Jalli +4
The success of large language models (LLMs) depends heavily on large-scale, high-quality instruction-following and reinforcement datasets. However, generating such data through hum…