Viktoriia A. Chekalina
4 papers · 2024–2026 · 3 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 ↓
🌍
Conference Polyglot · Bronze
🗺️
Taxonomy Completionist
(10)
Top co-authors
Research topics
Keywords
gradient sparsity
(2)
multimodal learning
(1)
neural network optimization
(1)
fisher information
(1)
hessian approximation
(1)
parameter-efficient fine-tuning
(1)
tool use
(1)
retrieval-augmented generation
(1)
sparse gradient
(1)
dialogue system
(1)
backward pass
(1)
large language model
(1)
transformer model
(1)
kronecker factorization
(1)
mlp layer
(1)
model quantization
(1)
second-order curvature
(1)
Papers
Acceleration of Backpropagation in Linear Layers of Transformer Models Based on Gradient Structure
EACL 2026
Fast and Accurate Fisher-Guided Quantization via Efficient Kronecker Factorization
ACL 2026
From Standard Transformers to Modern LLMs: Bringing Dialogue Models, RAG, and Agents to the Classroom
EACL 2026
SparseGrad: A Selective Method for Efficient Fine-tuning of MLP Layers
EMNLP 2024