Xinyu Duan
16 papers · 2022–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
π Renaissance Researcher (7) π Cross-Pollinator (14) π Interdisciplinary Bridge π Conference Polyglot (6) πΊοΈ Taxonomy Completionist (40)
π
Conference Polyglot
(6)
π€
Dynamic Duo
(10)
π
Century Club
(16)
β‘
Prolific Year
(5)
β
The Questioner
(2)
ποΈ
Keyword Collector
(76)
Conferences
ACL (5)
AAAI (3)
EMNLP (3)
ICLR (3)
ACML (1)
COLING (1)
Top co-authors
Keywords
zero-shot learning
(2)
voice conversion
(2)
large language model
(2)
inference acceleration
(2)
speech synthesis
(2)
speculative decoding
(2)
arabic language processing
(2)
cognitive modeling
(1)
text generation
(1)
transfer learning
(1)
graph structure
(1)
commonsense knowledge
(1)
syntactic parsing
(1)
autoregressive generation
(1)
few-shot learning
(1)
flow matching
(1)
natural language understanding
(1)
feature distribution
(1)
abstract meaning representation
(1)
dependency parsing
(1)
Papers
Multi-Branch Self-Drafting for LLM Inference Acceleration
AAAI 2025
Accurate KV Cache Quantization with Outlier Tokens Tracing
ACL 2025
Rhythm Controllable and Efficient Zero-Shot Voice Conversion via Shortcut Flow Matching
ACL 2025
Beware of Calibration Data for Pruning Large Language Models
ICLR 2025
Alignment-Augmented Speculative Decoding with Alignment Sampling and Conditional Verification
EMNLP 2025
When and How to Grow? On Efficient Pre-training via Model Growth
ACML 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
Dialogues Are Not Just Text: Modeling Cognition for Dialogue Coherence Evaluation
AAAI 2024
High-order Joint Constituency and Dependency Parsing
COLING 2024
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
OpenSR: Open-Modality Speech Recognition via Maintaining Multi-Modality Alignment
ACL 2023
AraMUS: Pushing the Limits of Data and Model Scale for Arabic Natural Language Processing
ACL 2023
Revisiting Pre-trained Language Models and their Evaluation for Arabic Natural Language Processing
EMNLP 2022