Maxim Rakhuba
12 papers · 2020–2026 · 9 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (29) π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π§¬
Topic Evolution
π
Keyword Champion
(2)
ποΈ
Keyword Collector
(66)
π
Century Club Β· Bronze
Top co-authors
Research topics
Machine Learning
(10)
Deep Learning
(8)
Optimization & Theory Β· Machine Learning
(8)
Architectures
(6)
Optimization & Theory Β· Deep Learning
(5)
Mathematics & Optimization
(4)
Application Areas
(4)
Artificial Intelligence
(3)
Core AI
(3)
Core Methods
(3)
Mathematics
(3)
Techniques
(3)
Learning Types
(2)
Models
(2)
Optimization
(2)
Keywords
neural network compression
(3)
tensor decomposition
(3)
model compression
(3)
parameter efficiency
(2)
structured matrix
(2)
orthogonal finetuning
(2)
tensor train decomposition
(2)
weight matrix
(2)
parameter reduction
(2)
covariance estimation
(1)
model merging
(1)
knowledge distillation
(1)
adversarial robustness
(1)
high-dimensional statistics
(1)
model calibration
(1)
matrix factorization
(1)
matrix decomposition
(1)
differentiable programming
(1)
spectral norm
(1)
manifold structure
(1)
Papers
Matrix-Free Two-to-Infinity and One-to-Two Norms Estimation
AAAI 2026
OrthoFuse: Training-free Riemannian Fusion of Orthogonal Style-Concept Adapters for Diffusion Models
CVPR 2026
Knowledge Graph Completion with Mixed Geometry Tensor Factorization
AISTATS 2025
ProcrustesGPT: Compressing LLMs with Structured Matrices and Orthogonal Transformations
ACL 2025
Dimension-free Structured Covariance Estimation
COLT 2024
Group and Shuffle: Efficient Structured Orthogonal Parametrization
NeurIPS 2024
Tight and Efficient Upper Bound on Spectral Norm of Convolutional Layers
ECCV 2024
Training a Tucker Model With Shared Factors: a Riemannian Optimization Approach
AISTATS 2024
Towards Practical Control of Singular Values of Convolutional Layers
NeurIPS 2022
Cherry-Picking Gradients: Learning Low-Rank Embeddings of Visual Data via Differentiable Cross-Approximation
ICCV 2021
Spectral Tensor Train Parameterization of Deep Learning Layers
AISTATS 2021
T-Basis: a Compact Representation for Neural Networks
ICML 2020