Xueyuan Chen
8 papers · 2022–2025 · 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(21)
❓
The Questioner
Top co-authors
Research topics
Deep Learning
(7)
Machine Learning
(6)
Core Methods
(4)
Architectures
(3)
Learning Types · Deep Learning
(3)
Models
(3)
Artificial Intelligence
(2)
Natural Language Processing
(2)
Speech & Audio
(2)
Core AI
(2)
Learning Types · Machine Learning
(2)
Analysis
(1)
Application Areas
(1)
Applications
(1)
Processing
(1)
Keywords
graph neural network
(2)
graph classification
(2)
structural entropy
(2)
self-supervised learning
(2)
unsupervised representation learning
(1)
in-context learning
(1)
information bottleneck
(1)
speaker identity
(1)
spoken language understanding
(1)
vector quantization
(1)
multimodal learning
(1)
diffusion model
(1)
language model
(1)
node classification
(1)
discrete token
(1)
graph information bottleneck
(1)
latent diffusion model
(1)
semantic prior
(1)
speech processing
(1)
graph clustering
(1)
Papers
ALMTokenizer: A Low-bitrate and Semantic-rich Audio Codec Tokenizer for Audio Language Modeling
ICML 2025
DiffDSR: Dysarthric Speech Reconstruction Using Latent Diffusion Model
Interspeech 2025
Speech Discrete Tokens or Continuous Features? A Comparative Analysis for Spoken Language Understanding in SpeechLLMs
EMNLP 2025
CoLM-DSR: Leveraging Neural Codec Language Modeling for Multi-Modal Dysarthric Speech Reconstruction
Interspeech 2024
SimpleSpeech: Towards Simple and Efficient Text-to-Speech with Scalar Latent Transformer Diffusion Models
Interspeech 2024
SEGA: Structural Entropy Guided Anchor View for Graph Contrastive Learning
ICML 2023
Structural Entropy Guided Graph Hierarchical Pooling
ICML 2022
Unsupervised Multi-scale Expressive Speaking Style Modeling with Hierarchical Context Information for Audiobook Speech Synthesis
COLING 2022