Xinyu Duan
16 papers · 2022–2025 · 6 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 ↓+5 more ↓ Show less ↑
π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (46) π£ Hot Topic Early Bird π€ Dynamic Duo (10)
π
Renaissance Researcher
(5)
β
The Questioner
(2)
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(92)
Top co-authors
Research topics
Artificial Intelligence
(13)
Core AI
(11)
Deep Learning
(10)
Machine Learning
(8)
Learning Types Β· Deep Learning
(6)
Application Areas
(5)
Natural Language Processing
(4)
Speech & Audio
(4)
Learning Paradigms
(4)
Models
(4)
Optimization & Theory Β· Machine Learning
(4)
Optimization & Theory Β· Deep Learning
(4)
Generation
(3)
Synthesis
(3)
Learning Types Β· Machine Learning
(2)
Keywords
zero-shot learning
(3)
large language model
(3)
pre-trained language model
(2)
multi-task learning
(2)
voice conversion
(2)
inference acceleration
(2)
arabic language processing
(2)
speculative decoding
(2)
speech synthesis
(2)
domain adaptation
(1)
transfer learning
(1)
knowledge distillation
(1)
text generation
(1)
commonsense knowledge
(1)
feature distribution
(1)
few-shot learning
(1)
instruction following
(1)
dependency parsing
(1)
abstract meaning representation
(1)
style transfer
(1)
Papers
Accurate KV Cache Quantization with Outlier Tokens Tracing
ACL 2025
Alignment-Augmented Speculative Decoding with Alignment Sampling and Conditional Verification
EMNLP 2025
Beware of Calibration Data for Pruning Large Language Models
ICLR 2025
Multi-Branch Self-Drafting for LLM Inference Acceleration
AAAI 2025
Rhythm Controllable and Efficient Zero-Shot Voice Conversion via Shortcut Flow Matching
ACL 2025
Adaptive Feature-based Low-Rank Compression of Large Language Models via Bayesian Optimization
EMNLP 2024
Are Bert Family Good Instruction Followers? A Study on Their Potential And Limitations
ICLR 2024
AuG-KD: Anchor-Based Mixup Generation for Out-of-Domain Knowledge Distillation
ICLR 2024
Dialogues Are Not Just Text: Modeling Cognition for Dialogue Coherence Evaluation
AAAI 2024
High-order Joint Constituency and Dependency Parsing
COLING 2024
StyleSinger: Style Transfer for Out-of-Domain Singing Voice Synthesis
AAAI 2024
TransFace: Unit-Based Audio-Visual Speech Synthesizer for Talking Head Translation
ACL 2024
When and How to Grow? On Efficient Pre-training via Model Growth
ACML 2024
AraMUS: Pushing the Limits of Data and Model Scale for Arabic Natural Language Processing
ACL 2023
OpenSR: Open-Modality Speech Recognition via Maintaining Multi-Modality Alignment
ACL 2023
Revisiting Pre-trained Language Models and their Evaluation for Arabic Natural Language Processing
EMNLP 2022