8 citations · 14 across the 15 of their papers we have counts for
15 papers
FBLayout: Optimizing Memory Layout for Efficient LLM Finetuning on Mobile GPUs
Kahou Tam, Wei Niu, Yu Bao +3
Transformer-based models have enabled unprecedented capabilities across language, vision, and multimodal tasks. On-device fine-tuning of transformer models offers a privacy-preserv…
Beyond End-to-End: Dynamic Chain Optimization for Private LLM Adaptation on the Edge
Yebo Wu, Jingguang Li, Chunlin Tian +3
Federated fine-tuning enables privacy-preserving LLM adaptation but faces a critical bottleneck: the disparity between LLMs' high memory demands and edge devices' limited capacity.…
TRU: Targeted Reverse Update for Efficient Multimodal Recommendation Unlearning
Zhanting Zhou, KaHou Tam, Zeyu Ma +2
Multimodal recommendation systems (MRS) jointly model user-item interaction graphs and rich item content, but this tight coupling makes user data difficult to remove once learned.…
Floe: Federated Specialization for Real-Time LLM-SLM Inference
Chunlin Tian, Kahou Tam, Yebo Wu +4
Deploying large language models (LLMs) in real-time systems remains challenging due to their substantial computational demands and privacy concerns. We propose Floe, a hybrid feder…
FedHybrid: Breaking the Memory Wall of Federated Learning via Hybrid Tensor Management
Kahou Tam, Chunlin Tian, Li Li +2
Federated Learning (FL) emerges as a new learning paradigm that enables multiple devices to collaboratively train a shared model while preserving data privacy. However, one fundame…
Dissecting Federated-Graph Aggregation under Domain Shift: Importance-Aware Aggregation via Empirical Analysis
Zhanting Zhou, Kahou Tam, Zeyu Ma +1
Federated graph learning (FGL) trains a shared graph model across clients whose local graphs differ in node features, labels, and connectivity while keeping raw graph data decentra…
CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge
Chunlin Tian, Xinpeng Qin, Kahou Tam +5
Deploying large language models (LLMs) on edge devices is crucial for delivering fast responses and ensuring data privacy. However, the limited storage, weight, and power of edge d…
A Survey on Federated Fine-tuning of Large Language Models
Yebo Wu, Chunlin Tian, Jingguang Li +8
Large Language Models (LLMs) have demonstrated impressive success across various tasks. Integrating LLMs with Federated Learning (FL), a paradigm known as FedLLM, offers a promisin…
Breaking the Memory Wall for Heterogeneous Federated Learning via Model Splitting
Chunlin Tian, Li Li, Kahou Tam +2
Federated Learning (FL) enables multiple devices to collaboratively train a shared model while preserving data privacy. Ever-increasing model complexity coupled with limited memory…
When, Where, and What? A Novel Benchmark for Accident Anticipation and Localization with Large Language Models
Haicheng Liao, Yongkang Li, Chengyue Wang +6
As autonomous driving systems increasingly become part of daily transportation, the ability to accurately anticipate and mitigate potential traffic accidents is paramount. Traditio…
CRASH: Crash Recognition and Anticipation System Harnessing with Context-Aware and Temporal Focus Attentions
Haicheng Liao, Haoyu Sun, Huanming Shen +6
Accurately and promptly predicting accidents among surrounding traffic agents from camera footage is crucial for the safety of autonomous vehicles (AVs). This task presents substan…
Towards Federated Domain Unlearning: Verification Methodologies and Challenges
Kahou Tam, Kewei Xu, Li Li +1
Federated Learning (FL) has evolved as a powerful tool for collaborative model training across multiple entities, ensuring data privacy in sensitive sectors such as healthcare and…
Characterized Diffusion and Spatial-Temporal Interaction Network for Trajectory Prediction in Autonomous Driving
Haicheng Liao, Xuelin Li, Yongkang Li +7
Trajectory prediction is a cornerstone in autonomous driving (AD), playing a critical role in enabling vehicles to navigate safely and efficiently in dynamic environments. To addre…
Breaking On-device Training Memory Wall: A Systematic Survey
Shitian Li, Chunlin Tian, Kahou Tam +2
On-device training has become an increasingly popular approach to machine learning, enabling models to be trained directly on mobile and edge devices. However, a major challenge in…
Federated Noisy Client Learning
Kahou Tam, Li Li, Bo Han +2
Federated learning (FL) collaboratively trains a shared global model depending on multiple local clients, while keeping the training data decentralized in order to preserve data pr…