Vadim Popov
9 papers · 2018–2026 · 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 ↓+2 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Bronze 🏃 Academic Marathon · Sprint 🗺️ Taxonomy Completionist (18) 🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Bronze
🚀
Conference Pioneer
📈
Trend Setter
Venues
Top co-authors
Research topics
Keywords
diffusion probabilistic model
(4)
voice conversion
(3)
stochastic differential equation
(3)
speech synthesis
(3)
model compression
(2)
maximum likelihood
(1)
score matching
(1)
generative model
(1)
diffusion model
(1)
gradient compression
(1)
language model
(1)
denoising diffusion
(1)
sparse autoencoder
(1)
perplexity reduction
(1)
concept erasure
(1)
cpu efficiency
(1)
on-device inference
(1)
sampling algorithm
(1)
neural vocoder
(1)
distributed fine-tuning
(1)
Papers
AudioSAE: Towards Understanding of Audio-Processing Models with Sparse AutoEncoders
EACL 2026
Improved Sampling Algorithms for Lévy-Itô Diffusion Models
ICLR 2025
PitchFlow: adding pitch control to a Flow-matching based TTS model
Interspeech 2024
A Unified System for Voice Cloning and Voice Conversion through Diffusion Probabilistic Modeling
Interspeech 2022
Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme
ICLR 2022
Fast Grad-TTS: Towards Efficient Diffusion-Based Speech Generation on CPU
Interspeech 2022
Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech
ICML 2021
Fast and Lightweight On-Device TTS with Tacotron2 and LPCNet
Interspeech 2020
Distributed Fine-tuning of Language Models on Private Data
ICLR 2018