Get started
Author

Aleksandr Beznosikov

Bridging Compressed Communication and Local Steps via Spectral Method in Federated Learning
2026 · Bystrov, Dmitriy, Chirkov, George, et al. · arXiv (Cornell University)
PDF
Multi-Stream Residual Computation in Diffusion Language Models
2026 · Alimaskina, Ekaterina, Kazarian, Suren, et al. · arXiv (Cornell University)
PDF
Not All Drift Is a Mechanism: Tracing Prompt Adaptation in LLMs
2026 · Aleksandrov, Mikhail, Bashirov, Nail, et al. · arXiv (Cornell University)
PDF
Monarch-Muon: Structure-Aware Muon for Fast and Memory-Efficient Pretraining
2026 · Miasnikov, Alexander, Kabirov, Ruslan, et al. · arXiv (Cornell University)
PDF
Spectral Weight Decay: Inducing Low-Rank Structure in Neural Network Weights
2026 · Andriianov, Dmitrii, Veprikov, Andrey, et al. · arXiv (Cornell University)
PDF
Mask-Guided KV Cache Eviction in Block Diffusion Language Models
2026 · Molodtsov, Gleb, Alimaskina, Ekaterina, et al. · arXiv (Cornell University)
PDF
LoRA-TSD: Tangent-Space Spectral Descent for LoRA via Muon-Style Updates
2026 · Andriianov, Dmitrii, Veprikov, Andrey, et al. · arXiv (Cornell University)
PDF
Controlling Refusal Behavior of LLMs via Stiefel-Constrained Rotation Steering
2026 · Bunin, Kirill, Bylinkin, Dmitry, et al. · arXiv (Cornell University)
PDF
Leveraging Association Context Retrieval in Knowledge Edit- ing to Build White-Box Attacks on LLMs
2026 · Maksimov, Roman, Aletov, Vladimir, et al. · arXiv (Cornell University)
PDF
The Kuramoto Neural Operator: Learning to Solve PDEs via Coupled Oscillator Dynamics
2026 · Badolia, Petr, Obukhov, Leonid, et al. · arXiv (Cornell University)
PDF
Self-Study Reconsidered: The Hidden Fragility of Learning from Self-Generated QA
2026 · Alimaskina, Ekaterina, Shveykin, Denis, et al. · arXiv (Cornell University)
PDF
WeightLoRA: Keep Only Necessary Adapters
2026 · Association for Computational Linguistics 2026, Alexander, Zyl, et al. · Underline Science Inc.
Analyzing Stream Collapse in Hyper-Connections: From Diagnosis to Mitigation
2026 · Alimaskina, Ekaterina, Molodtsov, Gleb, et al. · arXiv (Cornell University)
PDF
Softsign: Smooth Sign in Your Optimizer For Better Parameter Heterogeneity Handling
2026 · Feoktistov, Dmitrii, Belinsky, Timofey, et al. · arXiv (Cornell University)
PDF
LionMuon: Alternating Spectral and Sign Descent for Efficient Training
2026 · Bolatov, Arman, Riabinin, Artem, et al. · arXiv (Cornell University)
PDF
Beyond SGD, Without SVD: Proximal Subspace Iteration LoRA with Diagonal Fractional K-FAC
2026 · Almansoori, Abdulla Jasem, Ivanova, Maria, et al. · arXiv (Cornell University)
PDF
Exploring New Frontiers in Vertical Federated Learning: the Role of Saddle Point Reformulation
2026 · Beznosikov, Aleksandr, Kormakov, Georgiy, et al. · arXiv (Cornell University)
PDF
Zero-Order Optimization for LLM Fine-Tuning via Learnable Direction Sampling
2026 · Parfenov, Valery, Evseev, Grigoriy, et al. · arXiv (Cornell University)
PDF
Where Does Warm-Up Come From? Adaptive Scheduling for Norm-Constrained Optimizers
2026 · Riabinin, Artem, Veprikov, Andrey, et al. · arXiv (Cornell University)
PDF
Markovian Compression: Looking to the Past Helps Accelerate the Future
2026 · Veprikov, Andrey, Solodkin, Vladimir, et al. · arXiv (Cornell University)
PDF
HARP: Hadamard-Preconditioned Adaptive Rotation Processor for Extreme LLM Quantization
2026 · Artur Zagitov, Gleb Molodtsov, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
Rethinking the Role of Tensor Decompositions in Post-Training LLM Compression
2026 · Artur Zagitov, Alexander Miasnikov, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
WRDO: Weighted Refusal Direction Optimization in Aligned Language Models
2026 · Grigoriy Evseev, Vladimir Solodkin, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)
PDF
SimplexLoRA: Dynamic Rank Updating via Alternating Minimization with Simplex Projection
2026 · Shalygin Igor, Grigorii Davydenko, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)
PDF
High-Probability Convergence of Clipped SGD under Heavy-Tailed Noise and $(L_0,L_1)$-Smoothness
2025 · Kadi, Taha El Bakkali El, Chezhegov, Savelii, et al. · arXiv (Cornell University)
PDF
Works count: 25
Citation count:
H-index:
I10-index:
Year
Topic
Type