Ilia Kulikov
12 papers · 2020–2025 · 5 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 ↓+3 more ↓ Show less ↑
🗺️ Taxonomy Completionist (34) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🏆 Keyword Champion (2)
🗃️
Keyword Collector
(58)
🔥
Unstoppable · Bronze
💎
Century Club · Bronze
Top co-authors
Research topics
Machine Learning
(10)
Deep Learning
(9)
Natural Language Processing
(7)
Artificial Intelligence
(6)
Generation
(5)
Optimization & Theory
(5)
Core AI
(4)
Speech & Audio
(3)
Architectures
(3)
Learning Paradigms
(3)
Learning Types · Machine Learning
(3)
Learning Types · Deep Learning
(3)
Models
(3)
Application Areas
(2)
Applications
(2)
Keywords
beam search
(4)
speech synthesis
(3)
self-supervised learning
(2)
speech-to-speech translation
(2)
maximum likelihood
(2)
text generation
(2)
sequence generation
(2)
nucleus sampling
(2)
unlikelihood training
(2)
autoregressive model
(2)
large language model
(2)
machine translation
(1)
response generation
(1)
instruction following
(1)
dialogue generation
(1)
sequence modeling
(1)
neural machine translation
(1)
speech recognition
(1)
domain adaptation
(1)
noise robustness
(1)
Papers
Following Length Constraints in Instructions
EMNLP 2025
Investigating Decoder-only Large Language Models for Speech-to-text Translation
Interspeech 2024
Multi-resolution HuBERT: Multi-resolution Speech Self-Supervised Learning with Masked Unit Prediction
ICLR 2024
Textless Acoustic Model with Self-Supervised Distillation for Noise-Robust Expressive Speech-to-Speech Translation
ACL 2024
Simple and Effective Unsupervised Speech Translation
ACL 2023
UnitY: Two-pass Direct Speech-to-speech Translation with Discrete Units
ACL 2023
Characterizing and addressing the issue of oversmoothing in neural autoregressive sequence modeling
AACL 2022
Uncertainty Determines the Adequacy of the Mode and the Tractability of Decoding in Sequence-to-Sequence Models
ACL 2022
Mode recovery in neural autoregressive sequence modeling
ACL 2021
Consistency of a Recurrent Language Model With Respect to Incomplete Decoding
EMNLP 2020
Don’t Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training
ACL 2020
Neural Text Generation With Unlikelihood Training
ICLR 2020