← Authors

Xiaodong Cui

27 papers · 2017–2025 · 8 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🌈 Renaissance Researcher (5) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (8) πŸƒ Academic Marathon (8) 🐝 Cross-Pollinator (13) πŸ—ΊοΈ Taxonomy Completionist (41) πŸ† Keyword Champion (2) 🧬 Topic Evolution 🀝 Dynamic Duo (10) ⚑ Prolific Year (5) πŸ—ƒοΈ Keyword Collector (106) πŸ“ˆ Trend Setter πŸ’Ž Century Club (27) πŸ”₯ Unstoppable (9) ❓ The Questioner

Conferences

INTERSPEECH (12) NIPS (7) ICLR (2) ICML (2) ACL (1) AISTATS (1) IJCAI (1) IJCNLP (1)

Top co-authors

Wei Zhang (10) Brian Kingsbury (9) George Saon (9) Songtao Lu (7) Michael Picheny (6) Chia-Yu Chen (5) Kailash Gopalakrishnan (5) Swagath Venkataramani (5) ZoltΓ‘n TΓΌske (4) Pin-Yu Chen (4)

Keywords

automatic speech recognition (5) speech recognition (5) deep neural network (5) acoustic model (4) recurrent neural network transducer (4) model quantization (3) recurrent neural network (3) influence function (2) federated learning (2) word error rate (2) label smoothing (2) long short-term memory (2) distributed training (2) language model (2) efficient computing (2) decentralized optimization (2) model compression (2) distributed learning (2) neural network optimization (2) acoustic modeling (2)

Papers

Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis ICLR 2025
How Do Nonlinear Transformers Learn and Generalize in In-Context Learning? ICML 2024
M2ASR: Multilingual Multi-task Automatic Speech Recognition via Multi-objective Optimization INTERSPEECH 2024
Improving RNN Transducer Acoustic Models for English Conversational Speech Recognition INTERSPEECH 2023
Distributed Offline Policy Optimization Over Batch Data AISTATS 2023
Compressed Decentralized Proximal Stochastic Gradient Method for Nonconvex Composite Problems with Heterogeneous Data ICML 2023
A Stochastic Linearized Augmented Lagrangian Method for Decentralized Bilevel Optimization NIPS 2022
Accelerating Inference and Language Model Fusion of Recurrent Neural Network Transducers via End-to-End 4-bit Quantization INTERSPEECH 2022
Improving Generalization of Deep Neural Network Acoustic Models with Length Perturbation and N-best Based Label Smoothing INTERSPEECH 2022
On Sample Based Explanation Methods for NLP: Faithfulness, Efficiency and Semantic Evaluation ACL 2021
Reducing Exposure Bias in Training Recurrent Neural Network Transducers INTERSPEECH 2021
4-Bit Quantization of LSTM-Based Speech Recognition Models INTERSPEECH 2021
On Sample Based Explanation Methods for NLP: Faithfulness, Efficiency and Semantic Evaluation IJCNLP 2021
Task-Based Learning via Task-Oriented Prediction Network with Applications in Finance IJCAI 2020
Ultra-Low Precision 4-bit Training of Deep Neural Networks NIPS 2020
A Decentralized Parallel Algorithm for Training Generative Adversarial Nets NIPS 2020
ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training NIPS 2020
Towards Better Understanding of Adaptive Gradient Algorithms in Generative Adversarial Nets ICLR 2020
Hybrid 8-bit Floating Point (HFP8) Training and Inference for Deep Neural Networks NIPS 2019
Acoustic Model Optimization Based on Evolutionary Stochastic Gradient Descent with Anchors for Automatic Speech Recognition INTERSPEECH 2019
A Highly Efficient Distributed Deep Learning System for Automatic Speech Recognition INTERSPEECH 2019
Large-Scale Mixed-Bandwidth Deep Neural Network Acoustic Modeling for Automatic Speech Recognition INTERSPEECH 2019
Challenging the Boundaries of Speech Recognition: The MALACH Corpus INTERSPEECH 2019
Evolutionary Stochastic Gradient Descent for Optimization of Deep Neural Networks NIPS 2018
Dilated Recurrent Neural Networks NIPS 2017
Embedding-Based Speaker Adaptive Training of Deep Neural Networks INTERSPEECH 2017
English Conversational Telephone Speech Recognition by Humans and Machines INTERSPEECH 2017