Dimitrios Dimitriadis

Amazon (United States) — United States

Computer Science · Physical Sciences

22h-index1.6kcitations104works2.62yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Speech Recognition and Synthesis(48), Speech and Audio Processing(48), Music and Audio Processing(38), Privacy-Preserving Technologies in Data(18), Topic Modeling(10)

Publications104 total

GPT-FL: Generative Pre-Trained Model-Assisted Federated Learning
2025· 1 cited
The Federation Strikes Back: A Survey of Federated Learning Privacy Attacks, Defenses, Applications, and Policy Landscape
ACM Computing Surveys·2025· 21 citedOpen Access
Leveraging Uncertainty Estimation for Efficient LLM Routing
arXiv (Cornell University)·2025Open Access
Do Not Design, Learn: A Trainable Scoring Function for Uncertainty Estimation in Generative LLMs
2025Open Access
CroMo-Mixup: Augmenting Cross-Model Representations for Continual Self-Supervised Learning
Lecture notes in computer science·2024· 1 cited
Can Synthetic Audio From Generative Foundation Models Assist Audio Recognition and Speech Modeling?
2024· 4 cited
CroMo-Mixup: Augmenting Cross-Model Representations for Continual Self-Supervised Learning
arXiv (Cornell University)·2024Open Access
Predicting Uncertainty of Generative LLMs with MARS: Meaning-Aware Response Scoring
2024
Do Not Design, Learn: A Trainable Scoring Function for Uncertainty Estimation in Generative LLMs
arXiv (Cornell University)·2024Open Access
Can Synthetic Audio From Generative Foundation Models Assist Audio Recognition and Speech Modeling?
arXiv (Cornell University)·2024Open Access
Development and validation of words in babble test in the modern Greek language
Hearing Balance and Communication·2024· 1 citedOpen Access
MARS: Meaning-Aware Response Scoring for Uncertainty Estimation in Generative LLMs
arXiv (Cornell University)·2024· 1 citedOpen Access
Development and Validation of an Efficient and Safe Loud Music Exposure Paradigm
Journal of Speech Language and Hearing Research·2024· 4 citedOpen Access
MARS: Meaning-Aware Response Scoring for Uncertainty Estimation in Generative LLMs
2024· 4 citedOpen Access
Local or Global: Selective Knowledge Assimilation for Federated Learning with Limited Labels
2023· 10 cited
Federated benchmarking of medical artificial intelligence with MedPerf
Nature Machine Intelligence·2023· 107 citedOpen Access
Local or Global: Selective Knowledge Assimilation for Federated Learning with Limited Labels
arXiv (Cornell University)·2023· 1 citedOpen Access
Learning to Specialize: Joint Gating-Expert Training for Adaptive MoEs in Decentralized Settings
arXiv (Cornell University)·2023· 1 citedOpen Access
Counterfactual Augmentation for Multimodal Learning Under Presentation Bias
arXiv (Cornell University)·2023· 1 citedOpen Access
Distribution Inference Risks: Identifying and Mitigating Sources of Leakage
2023· 8 citedOpen Access
page 1 of 6Next →

Frequent Co-authors

Alexandros Potamianos(8), Petros Maragos(8), Takuya Yoshioka(6), Zhuo Chen(4), Xuedong Huang(4), Changliang Liu(4), Zakaria Aldeneh(4), Emily Mower Provost(4), Enrico Bocchieri(4), Robert B. Sim(3), Andreas Stolcke(3), Soheil Khorram(3), Kenichi Kumatani(3), Robert Gmyr(3), Şefik Emre Eskimez(3), Pirros Tsiakoulis(3), Petros Maragos(2), Yae Jee Cho(2), Andre Manoel(2), Igor Abramovski(2)