SFLAM is a quantized split federated fine-tuning framework for large AI models that reduces device memory, energy use, and latency via split learning, optimization strategies, and simulations showing gains over conventional methods.
Ungoliant: An optimized pipeline for the generation of a very large-scale multilingual web corpus,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Deploying Large AI Models on Resource-Limited Devices with Split Federated Learning
SFLAM is a quantized split federated fine-tuning framework for large AI models that reduces device memory, energy use, and latency via split learning, optimization strategies, and simulations showing gains over conventional methods.