4 citations · 6 across the 22 of their papers we have counts for
14 papers · 1 filter
Cross-Facility LLM Pre-training on HPC: Elastic Aggregation, Data Leasing, and Queue-Aware Placement
Zarè Palanciyan, Thomas van Osch, Douwe van der Wal +2
Academic compute is fragmented: allocations are granted per facility, and facilities differ in accelerators and software stacks, schedule jobs independently, and share neither a ne…
From Pilots to Production: Lessons in Cross-Institutional Federated Training and Artificial Intelligence for Science
Olivera Kotevska, Max Carlson, Yan Gao +10
Many of the most valuable scientific datasets cannot be centralized: they are proprietary, export-controlled, classified, or bound by data-sovereignty restrictions. This inverts th…
Privacy Foundations for Multi-Institutional Scientific Artificial Intelligence
Olivera Kotevska, Sumit Jha, Aur'elien Bellet +6
Scientific artificial intelligence (AI), spanning foundation models (FMs) to federated data-analysis pipelines, is becoming shared infrastructure across national laboratories, univ…
Forgetting Only What Matters: Layer-Selective Unlearning toward Robust LLMs
Ravi Ranjan, Olivera Kotevska, Agoritsa Polyzou
Large Language Models (LLMs) can memorize and reproduce sensitive, copyrighted, or otherwise undesirable training content, creating privacy, safety, and regulatory concerns. Machin…
Extending the Horizon of Early Diagnosis: Lung Cancer Prediction with Vision Transformers
Olivera Kotevska, Ian Goethert, Michael McGee +11
Lung cancer remains a leading cause of cancer-related mortality worldwide, and early diagnosis is critical for improving survival. However, early-stage malignancies can be subtle o…
Consilience: Conformally Calibrated Communication Control for Hidden-Profile Multi-Agent Reasoning
Abhijith Babu, Ramneet Kaur, Vishal Pramanik +7
Multi-agent LLM systems can improve reasoning by pooling diverse perspectives, but their effectiveness depends on coordinating communication, particularly in hidden-profile setting…
Enforcing LLM Safety through DMD-based Classification of Prompt-Response Embedding Dynamics
Mohamed Akrout, Olivera Kotevska, Dan Wilson
Large Language Models (LLMs) are increasingly deployed in high-stakes applications, yet their tendency to generate toxic, harmful, or policy-violating content poses significant ris…
IntraShuffler: A Privacy Preserving Framework for Heterogeneous DP Federated Learning
Farhin Farhad Riya, Olivera Kotevska, Jinyuan Stella Sun
Heterogeneous Differential Privacy (HDP) in Federated Learning (FL) allows clients to select individual privacy budgets () according to institutional policies and da…
Vision Token Manipulation Attacks on Cloud-Edge Inference of Large Vision-Language Models
Zikai Zhang, Rui Hu, Olivera Kotevska +1
Cloud-edge Large Vision-Language Model (LVLM) inference enables efficient deployment by splitting computation between edge devices and cloud servers. In this process, intermediate…
Closed-Loop Neural Activation Control in Vision-Language-Action Models
Abhijith Babu, Ramneet Kaur, Nathaniel D. Bastian +5
Vision-Language-Action (VLA) models can be steered at test time by intervening on semantically meaningful internal directions, but existing methods use a fixed steering coefficient…
SelfGrader: LLM Jailbreak Detection via Anchored Token-Level Logits
Zikai Zhang, Rui Hu, Olivera Kotevska +1
Large Language Models (LLMs) are powerful tools for answering user queries, yet they remain highly vulnerable to jailbreak attacks. Existing guardrail methods typically rely on int…
Provably Communication-Efficient and Privacy-Preserving Federated Graph Neural Networks
Zhishuai Guo, Wenhan Wu, Chen Chen +3
Graph neural networks (GNNs) achieve strong performance on relational data, but real-world graphs are often distributed across organizations that cannot share raw data due to priva…
XMark: Reliable Multi-Bit Watermarking for LLM-Generated Texts
Jiahao Xu, Rui Hu, Olivera Kotevska +1
Multi-bit watermarking has emerged as a promising solution for embedding imperceptible binary messages into Large Language Model (LLM)-generated text, enabling reliable attribution…
Automated Membership Inference Attacks (AutoMIA): Discovering MIA Signal Computations using LLM Agents
Toan Tran, Olivera Kotevska, Li Xiong
Membership inference attacks (MIAs), which enable adversaries to determine whether specific data points were part of a model's training dataset, have emerged as an important framew…