Publications (22)
Less is More: Removing Text-regions Improves CLIP Training Efficiency and Robustness
Liangliang Cao, Bowen Zhang, Chen Chen +5
E2E Segmenter: Joint Segmenting and Decoding for Long-Form ASR
W. Ronny Huang, Shuo-yiin Chang, David Rybach +5
Mean-Field Approximation to Gaussian-Softmax Integral with Application to Uncertainty Estimation
Zhiyun Lu, Eugene Ie, Fei Sha
Hyper-parameter Tuning under a Budget Constraint
Zhiyun Lu, Chao-Kai Chiang, Fei Sha
Improving the fusion of acoustic and text representations in RNN-T
Chao Zhang, Bo Li, Zhiyun Lu +2
Kernel Approximation Methods for Speech Recognition
Avner May, Alireza Bagheri Garakani, Zhiyun Lu +9
Input Length Matters: Improving RNN-T and MWER Training for Long-form Telephony Speech Recognition
Zhiyun Lu, Yanwei Pan, Thibault Doutre +5
Speech Sentiment Analysis via Pre-trained Features from End-to-end ASR Models
Zhiyun Lu, Liangliang Cao, Yu Zhang +2
Talking Turns: Benchmarking Audio Foundation Models on Turn-Taking Dynamics
Siddhant Arora, Zhiyun Lu, Chung-Cheng Chiu +2
Unsupervised Data Selection via Discrete Speech Representation for ASR
Zhiyun Lu, Yongqiang Wang, Yu Zhang +3
A Comparison between Deep Neural Nets and Kernel Acoustic Models for Speech Recognition
Zhiyun Lu, Dong Guo, Alireza Bagheri Garakani +8
Improving Streaming Automatic Speech Recognition With Non-Streaming Model Distillation On Unsupervised Data
Thibault Doutre, Wei Han, Min Ma +7
Apple Intelligence Foundation Language Models: Tech Report 2025
Ethan Li, Anders Boesen Lindbo Larsen, Chen Zhang +395
Apple Intelligence Foundation Language Models
Tom Gunter, Zirui Wang, Chong Wang +152
Instruction-Following Speech Recognition
Cheng-I Jeff Lai, Zhiyun Lu, Liangliang Cao +1
Data-Centric Lessons To Improve Speech-Language Pretraining
Vishaal Udandarao, Zhiyun Lu, Xuankai Chang +6
How to Scale Up Kernel Methods to Be As Good As Deep Neural Nets
Zhiyun Lu, Avner May, Kuan Liu +8
Direct Large Language Model Alignment Through Self-Rewarding Contrastive Prompt Distillation
Aiwei Liu, Haoping Bai, Zhiyun Lu +5
AXLearn: Modular, Hardware-Agnostic Large Model Training
Mark Lee, Chang Lan, Tom Gunter +34
Exploring Targeted Universal Adversarial Perturbations to End-to-end ASR Models
Zhiyun Lu, Wei Han, Yu Zhang +1
Learning Compact Recurrent Neural Networks
Zhiyun Lu, Vikas Sindhwani, Tara N. Sainath
TIS-DPO: Token-level Importance Sampling for Direct Preference Optimization With Estimated Weights
Aiwei Liu, Haoping Bai, Zhiyun Lu +9