Showing 2026Show all
2 papers · 1 filter
cs.AI2026
Routing Without Training: Controllable-Ratio LLM Offloading via Reliability Gating
Evan Chen, Shiqiang Wang, Kevin S Chan +2
Local-cloud collaboration is a practical way to deploy large language models under resource constraints, but existing methods often rely on trained routers or collaboration-aware f…
cs.LG2026
Joint Continual Learning of Local Language Models and Cloud Offloading Decisions with Budget Constraints
Evan Chen, Wenzhi Fang, Shiqiang Wang +1
Locally deployed Small Language Models (SLMs) must continually support diverse tasks under strict memory and computation constraints, making selective reliance on cloud Large Langu…