11 citations · 22 across the 9 of their papers we have counts for
9 papers
Enhancing Small Language Models for Power Outage Report Generation via Minimum Risk Training
Hung Phan, Waqwoya Abebe, Youssef Hussein +3
Minimum Risk Training (MRT) enables neural machine translation models to directly optimize sequence-level evaluation metrics instead of relying only on token- level maximum-likelih…
Emerging Flexible Designs for Geospatial Multimodal Foundation Models
Philipe Dias, Waqwoya Abebe, Abhishek Potnis +4
Foundation models are rapidly transforming Earth observation by enabling scalable pretraining across diverse unlabeled geospatial modalities. However, their architectural diversity…
GeoGNN: Time Series Geo-Localization using Two-Tower Graph Neural Networks
Toan Tran, Waqwoya Abebe, Abhishek Potnis +4
This paper investigates a novel concept of time series geolocalization, where the goal is to infer the geographic origin of each raw time series. Successful geolocalization can pro…
SuperSAM: Crafting a SAM Supernetwork via Structured Pruning and Unstructured Parameter Prioritization
Waqwoya Abebe, Sadegh Jafari, Sixing Yu +6
Neural Architecture Search (NAS) is a powerful approach of automating the design of efficient neural architectures. In contrast to traditional NAS methods, recently proposed one-sh…
SAM-I-Am: Semantic Boosting for Zero-shot Atomic-Scale Electron Micrograph Segmentation
Waqwoya Abebe, Jan Strube, Luanzheng Guo +5
Image segmentation is a critical enabler for tasks ranging from medical diagnostics to autonomous driving. However, the correct segmentation semantics - where are boundaries locate…
The Landscape and Challenges of HPC Research and LLMs
Le Chen, Nesreen K. Ahmed, Akash Dutta +14
Recently, language models (LMs), especially large language models (LLMs), have revolutionized the field of deep learning. Both encoder-decoder models and prompt-based techniques ha…
LEFL: Low Entropy Client Sampling in Federated Learning
Waqwoya Abebe, Pablo Munoz, Ali Jannesari
Federated learning (FL) is a machine learning paradigm where multiple clients collaborate to optimize a single global model using their private data. The global model is maintained…
Addressing Data Heterogeneity in Decentralized Learning via Topological Pre-processing
Waqwoya Abebe, Ali Jannesari
Recently, local peer topology has been shown to influence the overall convergence of decentralized learning (DL) graphs in the presence of data heterogeneity. In this paper, we dem…
SPATL: Salient Parameter Aggregation and Transfer Learning for Heterogeneous Clients in Federated Learning
Sixing Yu, Phuong Nguyen, Waqwoya Abebe +3
Federated learning~(FL) facilitates the training and deploying AI models on edge devices. Preserving user data privacy in FL introduces several challenges, including expensive comm…