3 papers
cs.LG2026
LEMUR 2: Unlocking Neural Network Diversity for AI
Tolgay Atinc Uzun, Waleed Khalid, Saif U Din +17
Existing NAS benchmarks (e.g., NAS-Bench, NATS-Bench) cover only narrow, task-specific regions of the architectural design space and lack cross-domain or deployment-aware evaluatio…
cs.LG2026
Sustainable LLM Inference using Context-Aware Model Switching
Yuvarani, Akashdeep Singh, Zahra Fathanah +3
Large language models have become central to many AI applications, but their growing energy consumption raises serious sustainability concerns. A key limitation in current AI deplo…
cs.HC2026
LunaAI: A Polite and Fair Healthcare Guidance Chatbot
Yuvarani Ganesan, Salsabila Harlen, Azfar Rahman Bin Fazul Rahman +3
Conversational AI has significant potential in the healthcare sector, but many existing systems fall short in emotional intelligence, fairness, and politeness, which are essential…