Sergey Troshin
6 papers · 2021–2026 · 4 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 ↓+1 more ↓ Show less ↑
π Conference Polyglot Β· Bronze π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (16) π£ Hot Topic Early Bird
π
Trend Setter
Top co-authors
Research topics
Keywords
source code
(3)
angular dispersion
(2)
neural machine translation
(2)
machine translation
(1)
text generation
(1)
approximate nearest neighbor
(1)
k-nearest neighbor
(1)
language model
(1)
pre-trained model
(1)
representation collapse
(1)
sampling method
(1)
code representation
(1)
syntactic structure
(1)
response diversity
(1)
byte pair encoding
(1)
code understanding
(1)
semantic equivalence
(1)
probing task
(1)
hidden state representation
(1)
large language model
(1)
Papers
Representation Collapse in Machine Translation Through the Lens of Angular Dispersion
EACL 2026
Angular Dispersion Accelerates k-Nearest Neighbors Machine Translation
EMNLP 2025
Asking a Language Model for Diverse Responses
EMNLP 2025
CodeBPE: Investigating Subtokenization Options for Large Language Model Pretraining on Source Code
ICLR 2023
Probing Pretrained Models of Source Codes
EMNLP 2022
A Simple Approach for Handling Out-of-Vocabulary Identifiers in Deep Learning for Source Code
NAACL 2021