2 citations · 3 across the 10 of their papers we have counts for
6 papers · 1 filter
ACED: Reference-Anchored Aggregation of Natural-Language and Executable Evidence for Mathematical Reasoning
Yiyi Lu, Jiaxiang Geng, Bing Luo
Natural-language self-consistency and executable programs provide complementary test-time evidence for mathematical reasoning, yet either channel may support the same semantic erro…
MobileFineTuner: A Mobile-Native Framework for On-Device LLM Fine-Tuning in Real-World Embedded AI Applications
Jiaxiang Geng, Lunyu Zhao, Yiyi Lu +1
Large language models (LLMs) are moving from cloud-centric services toward on-device embedded AI, where models interact with private, longitudinal signals sensed from users and the…
Adaptive Federated LoRA in Heterogeneous Wireless Networks with Independent Sampling
Yanzhao Hou, Jiaxiang Geng, Boyu Li +4
Federated LoRA has emerged as a promising technique for efficiently fine-tuning large language models (LLMs) on distributed devices by reducing the number of trainable parameters.…
Ten Challenging Problems in Federated Foundation Models
Tao Fan, Hanlin Gu, Xuemei Cao +30
Federated Foundation Models (FedFMs) represent a distributed learning paradigm that fuses general competences of foundation models as well as privacy-preserving capabilities of fed…
WHALE-FL: Wireless and Heterogeneity Aware Latency Efficient Federated Learning over Mobile Devices via Adaptive Subnetwork Scheduling
Huai-an Su, Jiaxiang Geng, Liang Li +5
As a popular distributed learning paradigm, federated learning (FL) over mobile devices fosters numerous applications, while their practical deployment is hindered by participating…
Adaptive Federated Learning in Heterogeneous Wireless Networks with Independent Sampling
Jiaxiang Geng, Yanzhao Hou, Xiaofeng Tao +2
Federated Learning (FL) algorithms commonly sample a random subset of clients to address the straggler issue and improve communication efficiency. While recent works have proposed…