Ivan Kobyzev
17 papers · 2020–2026 · 7 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 ↓+6 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (33) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π€
Dynamic Duo
(12)
β
The Questioner
π₯
Unstoppable Β· Bronze
π
Century Club Β· Bronze
β‘
Prolific Year Β· Productive
ποΈ
Keyword Collector
(83)
Top co-authors
Research topics
Machine Learning
(15)
Deep Learning
(12)
Optimization & Theory Β· Machine Learning
(10)
Artificial Intelligence
(7)
Core Methods
(7)
Architectures
(6)
Core AI
(5)
Optimization & Theory Β· Deep Learning
(5)
Application Areas
(4)
Learning Types
(3)
Natural Language Processing
(2)
Learning Paradigms
(2)
Techniques
(2)
Mathematics & Optimization
(1)
Applications
(1)
Keywords
large language model
(3)
knowledge distillation
(3)
machine translation
(2)
model compression
(2)
representation learning
(2)
transformer architecture
(2)
label regularization
(2)
label smoothing
(2)
model efficiency
(2)
density estimation
(1)
dialogue generation
(1)
kl divergence
(1)
text generation
(1)
word alignment
(1)
matrix factorization
(1)
parameter efficient
(1)
error detection
(1)
attention mechanism
(1)
efficient computing
(1)
natural language understanding
(1)
Papers
BOSCH: Black-Box Binary Optimization for Short-Context Attention-Head Selection in LLMs
ACL 2026
Integral Transformer: Denoising Attention, Not Too Much Not Too Little
EMNLP 2025
ReGLA: Refining Gated Linear Attention
NAACL 2025
Draft on the Fly: Adaptive Self-Speculative Decoding using Cosine Similarity
EMNLP 2024
OTTAWA: Optimal TransporT Adaptive Word Aligner for Hallucination and Omission Translation Errors Detection
ACL 2024
Resonance RoPE: Improving Context Length Generalization of Large Language Models
ACL 2024
Attribute Controlled Dialogue Prompting
ACL 2023
Do we need Label Regularization to Fine-tune Pre-trained Language Models?
EACL 2023
DyLoRA: Parameter-Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptation
EACL 2023
Efficient Classification of Long Documents via State-Space Models
EMNLP 2023
LABO: Towards Learning Optimal Label Regularization via Bi-level Optimization
ACL 2023
Continuation KD: Improved Knowledge Distillation through the Lens of Continuation Optimization
EMNLP 2022
Improving Generalization of Pre-trained Language Models via Stochastic Weight Averaging
EMNLP 2022
Learning functions on multiple sets using multi-set transformers
UAI 2022
Polarized-VAE: Proximity Based Disentangled Representation Learning for Text Generation
EACL 2021
Representation Learning for Dynamic Graphs: A Survey
JMLR 2020
Tails of Lipschitz Triangular Flows
ICML 2020