Eugene Belilovsky

Computer Science · Physical Sciences

20h-index1.5kcitations124works1.02yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

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

Research Topics

Domain Adaptation and Few-Shot Learning(30), Multimodal Machine Learning Applications(17), Advanced Neural Network Applications(16), Generative Adversarial Networks and Image Synthesis(10), Topic Modeling(9)

Publications123 total

Heterogeneous Low-Bandwidth Pre-Training of LLMs
arXiv (Cornell University)·2026Open Access
Heterogeneous Low-Bandwidth Pre-Training of LLMs
ArXiv.org·2026Open Access
Incentivizing Permissionless Distributed Learning of LLMs
2025Open Access
When Data Falls Short: Grokking Below the Critical Threshold
arXiv (Cornell University)·2025Open Access
Test Time Adaptation Using Adaptive Quantile Recalibration
arXiv (Cornell University)·2025Open Access
Adaptive Local Training in Federated Learning
2025
Warming Up for Zeroth-Order Federated Pre-Training with Low Resource Clients
arXiv (Cornell University)·2025Open Access
Communication Efficient LLM Pre-training with SparseLoCo
arXiv (Cornell University)·2025Open Access
Rethinking Prompt Optimization: Reinforcement, Diversification, and Migration in Blackbox LLMs
arXiv (Cornell University)·2025Open Access
Model Parallelism With Subnetwork Data Parallelism
arXiv (Cornell University)·2025Open Access
Less is More: Undertraining Experts Improves Model Upcycling
arXiv (Cornell University)·2025Open Access
PyLO: Towards Accessible Learned Optimizers in PyTorch
arXiv (Cornell University)·2025Open Access
MuLoCo: Muon is a practical inner optimizer for DiLoCo
ArXiv.org·2025Open Access
Incentivizing Permissionless Distributed Learning of LLMs
arXiv (Cornell University)·2025Open Access
Large language models deconstruct the clinical intuition behind diagnosing autism
Cell·2025· 8 citedOpen Access
Unsupervised Test-Time Adaptation for Hepatic Steatosis Grading Using Ultrasound B-Mode Images
IEEE Transactions on Ultrasonics Ferroelectrics and Frequency Control·2025· 5 cited
Beyond Cosine Decay: On the effectiveness of Infinite Learning Rate Schedule for Continual Pre-training
arXiv (Cornell University)·2025Open Access
FairDropout: Using Example-Tied Dropout to Enhance Generalization of Minority Groups
arXiv (Cornell University)·2025· 1 citedOpen Access
Celo: Training Versatile Learned Optimizers on a Compute Diet
arXiv (Cornell University)·2025Open Access
Towards Motion from Video Diffusion Models
Lecture notes in computer science·2025
page 1 of 7Next →

Frequent Co-authors

Edouard Oyallon(11), Matthew B. Blaschko(10), Michael Eickenberg(8), Rahaf Aljundi(6), Irina Rish(6), Sergey Zagoruyko(5), Lucas Caccia(5), Aaron Courville(5), Guy Wolf(5), Gaël Varoquaux(5), Muawiz Chaudhary(5), Tinne Tuytelaars(4), MohammadReza Davari(4), Cătălina Cangea(4), M. Caccia(3), Nader Asadi(3), Sudhir P. Mudur(3), Joëlle Pineau(3), B. A. Knyazev(3), Harm de Vries(3)