6 papers
DP-LAC: Lightweight Adaptive Clipping for Differentially Private Federated Fine-tuning of Language Models
Haaris Mehmood, Jie Xu, Karthikeyan Saravanan +2
Federated learning (FL) enables the collaborative training of large-scale language models (LLMs) across edge devices while keeping user data on-device. However, FL still exposes se…
Guided Model Merging for Hybrid Data Learning: Leveraging Centralized Data to Refine Decentralized Models
Junyi Zhu, Ruicong Yao, Taha Ceritli +6
Current network training paradigms primarily focus on either centralized or decentralized data regimes. However, in practice, data availability often exhibits a hybrid nature, wher…
Mem-MLP: Real-Time 3D Human Motion Generation from Sparse Inputs
Sinan Mutlu, Georgios F. Angelis, Savas Ozkan +3
Realistic and smooth full-body tracking is crucial for immersive AR/VR applications. Existing systems primarily track head and hands via Head Mounted Devices (HMDs) and controllers…
Multi-Task Pre-Finetuning of Lightweight Transformer Encoders for Text Classification and NER
Junyi Zhu, Savas Ozkan, Andrea Maracani +3
Deploying natural language processing (NLP) models on mobile platforms requires models that can adapt across diverse applications while remaining efficient in memory and computatio…
Efficient 3D Full-Body Motion Generation from Sparse Tracking Inputs with Temporal Windows
Georgios Fotios Angelis, Savas Ozkan, Sinan Mutlu +3
To have a seamless user experience on immersive AR/VR applications, the importance of efficient and effective Neural Network (NN) models is undeniable, since missing body parts tha…
Accurate Scene Text Recognition with Efficient Model Scaling and Cloze Self-Distillation
Andrea Maracani, Savas Ozkan, Sijun Cho +6
Scaling architectures have been proven effective for improving Scene Text Recognition (STR), but the individual contribution of vision encoder and text decoder scaling remain under…