Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Request-Level Energy Attribution for Batched LLM Serving
Qi Luo, Kunlin Li, Ziwen Wang +2
Batched LLM serving improves throughput but complicates energy accounting. GPU power telemetry is aggregate, whereas sustainability reporting, chargeback, and workload analysis oft…
cs.AI2025
SwarmThinkers: Learning Physically Consistent Atomic KMC Transitions at Scale
Qi Li, Kun Li, Haozhi Han +6
Can a scientific simulation system be physically consistent, interpretable by design, and scalable across regimes--all at once? Despite decades of progress, this trifecta remains e…