8 citations · 14 across the 8 of their papers we have counts for
9 papers
Evaluation Bias and Epistemic Inequality in Global Software Development
Sam Khosravi, Amir H. Payberah
This paper examines fairness and accountability in global software development by focusing on how competence is assessed and valued across unequal regional contexts. We compare sof…
KG-FairDiff: Knowledge Graph-Guided Prompt Refinement for Demographically Fair Text-to-Image Generation
Farbod Davoodi, Seyed Reza Tavakoli Shiyadeh, Pooria Safaei +12
Text-to-Image (TTI) systems are now everyday infrastructure for journalism, education, advertising, and public communication, and the demographic and cultural stereotypes they inhe…
PBBQ: A Persian Bias Benchmark Dataset Curated with Human-AI Collaboration for Large Language Models
Farhan Farsi, Shayan Bali, Fatemeh Valeh +4
With the increasing adoption of large language models (LLMs), ensuring their alignment with social norms has become a critical concern. While prior research has examined bias detec…
Who Gets the Mic? Investigating Gender Bias in the Speaker Assignment of a Speech-LLM
Dariia Puhach, Amir H. Payberah, Éva Székely
Similar to text-based Large Language Models (LLMs), Speech-LLMs exhibit emergent abilities and context awareness. However, whether these similarities extend to gender bias remains…
AquaCluster: Using Satellite Images And Self-supervised Machine Learning Networks To Detect Water Hidden Under Vegetation
Ioannis Iakovidis, Zahra Kalantari, Amir Hossein Payberah +2
In recent years, the wide availability of high-resolution radar satellite images has enabled the remote monitoring of wetland surface areas. Machine learning models have achieved s…
ContrastNER: Contrastive-based Prompt Tuning for Few-shot NER
Amirhossein Layegh, Amir H. Payberah, Ahmet Soylu +2
Prompt-based language models have produced encouraging results in numerous applications, including Named Entity Recognition (NER) tasks. NER aims to identify entities in a sentence…
DeepAqua: Self-Supervised Semantic Segmentation of Wetland Surface Water Extent with SAR Images using Knowledge Distillation
Francisco J. Peña, Clara Hübinger, Amir H. Payberah +1
Deep learning and remote sensing techniques have significantly advanced water monitoring abilities; however, the need for annotated data remains a challenge. This is particularly p…
Accelerate Model Parallel Training by Using Efficient Graph Traversal Order in Device Placement
Tianze Wang, Amir H. Payberah, Desta Haileselassie Hagos +1
Modern neural networks require long training to reach decent performance on massive datasets. One common approach to speed up training is model parallelization, where large neural…
Converging an Overlay Network to a Gradient Topology
Håkan Terelius, Guodong Shi, Jim Dowling +3
In this paper, we investigate the topology convergence problem for the gossip-based Gradient overlay network. In an overlay network where each node has a local utility value, a Gra…