Cunxiao Du
14 papers · 2019–2026 · 7 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 ↓+6 more ↓ Show less ↑
🗺️ Taxonomy Completionist (22) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird
🧬
Topic Evolution
🏆
Keyword Champion
(7)
🗃️
Keyword Collector
(56)
💎
Century Club · Bronze
⚡
Prolific Year · Productive
🚀
Conference Pioneer
Top co-authors
Research topics
Artificial Intelligence
(9)
Machine Learning
(9)
Natural Language Processing
(8)
Deep Learning
(7)
Core AI
(7)
Optimization & Theory · Machine Learning
(6)
Applications
(4)
Resources & Methods
(3)
Techniques
(3)
Application Areas
(2)
Architectures
(2)
Generation
(2)
Learning Paradigms
(2)
Optimization & Theory · Deep Learning
(2)
Computer Vision
(1)
Keywords
speculative decoding
(7)
inference acceleration
(4)
large language model
(4)
autoregressive model
(2)
cross entropy
(2)
key-value cache
(2)
non-autoregressive translation
(2)
machine translation
(2)
text understanding
(1)
stochastic reward
(1)
fine-grained classification
(1)
markov model
(1)
diffusion model
(1)
attention mechanism
(1)
iterative refinement
(1)
continued pretraining
(1)
video understanding
(1)
adversarial reward
(1)
layer skipping
(1)
bandit algorithm
(1)
Papers
Annealed Relaxation of Speculative Decoding for Faster Autoregressive Image Generation
AAAI 2026
LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification
ACL 2026
Merlin’s Whisper: Enabling Efficient Reasoning in Large Language Models via Black-box Persuasive Prompting
ACL 2026
BanditSpec: Adaptive Speculative Decoding via Bandit Algorithms
ICML 2025
Efficient Inference for Large Language Model-based Generative Recommendation
ICLR 2025
Reverse Modeling in Large Language Models
NAACL 2025
Sparse-to-Dense: A Free Lunch for Lossless Acceleration of Video Understanding in LLMs
ACL 2025
SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration
ICLR 2025
When Attention Sink Emerges in Language Models: An Empirical View
ICLR 2025
GliDe with a CaPE: A Low-Hassle Method to Accelerate Speculative Decoding
ICML 2024
Revisiting the Markov Property for Machine Translation
EACL 2024
ngram-OAXE: Phrase-Based Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation
COLING 2022
Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation
ICML 2021
Explicit Interaction Model towards Text Classification
AAAI 2019