4 papers
Responsible Federated LLMs via Safety Filtering and Constitutional AI
Eunchung Noh, Jeonghun Baek
Recent research has increasingly focused on training large language models (LLMs) using federated learning, known as FedLLM. However, responsible AI (RAI), which aims to ensure saf…
Let the Void Be Void: Robust Open-Set Semi-Supervised Learning via Selective Non-Alignment
You Rim Choi, Subeom Park, Seojun Heo +2
Open-set semi-supervised learning (OSSL) leverages unlabeled data containing both in-distribution (ID) and unknown out-of-distribution (OOD) samples, aiming simultaneously to impro…
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…
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…