Get started
Author

Martin Takáč

Observed names: Martin Takac, Takac, Martin, Takáč, Martin
OpenAlex ID: A5138691307
A Damped Newton Method Achieves Global O (1/k2) and Local Quadratic Convergence Rate
2022 · Slavomír Hanzely, Dmitry Kamzolov, et al. · neural information processing systems · 2
Tropical Reinforcement Learning
2026 · Asadulaev, Arip, Djuhera, Aladin, et al. · arXiv (Cornell University)
PDF
Optimizers for Diffusion Models: A Controlled Benchmark
2026 · Bolatov, Arman, Shulgin, Egor, et al. · arXiv (Cornell University)
PDF
Certified Residual Quasi-Newton Methods for Distributed Variational Inequalities
2026 · Obzherin, Ewsey R., Mozhaev, Roman M., et al. · arXiv (Cornell University)
PDF
Score-Only Distillation for Compact Dense Retrieval
2026 · Dubovikov, Kirill, Takac, Martin, et al. · arXiv (Cornell University)
PDF
PETRA: Transforming Web Text for Petroleum-Engineering Domain Adaptation
2026 · Dubovikov, Kirill, Mansouri, Omar El, et al. · arXiv (Cornell University)
PDF
Privacy from Symmetry: Orthogonally Equivariant Transformers for LLM Inference
2026 · Yukhimchuk, Alexander, Shulga, Andrey, et al. · arXiv (Cornell University)
PDF
Entropy-Gated Latent Recursion
2026 · Bhattacharjee, Soham, Chauhan, Dushyant Singh, et al. · arXiv (Cornell University)
PDF
Chebyshev-Exact Acceleration under Hessian Variation, I: Sine-Jacobi Method
2026 · Pasechnyuk-Vilensky, Dmitry, Takáč, Martin · arXiv (Cornell University)
PDF
Value-Gradient Hypothesis of RL for LLMs
2026 · Asadulaev, Arip, Ognev, Daniil, et al. · arXiv (Cornell University)
PDF
Muon with Nesterov Momentum: Heavy-Tailed Noise and (Randomized) Inexact Polar Decomposition
2026 · Choudhury, Sayantan, Cheng, Xiaoran, et al. · arXiv (Cornell University)
PDF
CopyShield: A Cross-Level Benchmark of Copyright Defenses in LLMs
2026 · Maryam Alshehyari, Dushyant Singh Chauhan, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
Works count: 12
Citation count: 2
H-index: 1
I10-index:
Year
Topic
Type