4 papers
Steering LLMs for Culturally Localized Generation
Simran Khanuja, Hongbin Liu, Shujian Zhang +4
LLMs are deployed globally, yet produce responses biased towards cultures with abundant training data. Existing cultural localization approaches such as prompting or post-training…
Scalable Training of Mixture-of-Experts Models with Megatron Core
Zijie Yan, Hongxiao Bai, Xin Yao +42
Scaling Mixture-of-Experts (MoE) training introduces systems challenges absent in dense models. Because each token activates only a subset of experts, this sparsity allows total pa…
Can DeepFake Speech be Reliably Detected?
Hongbin Liu, Youzheng Chen, Arun Narayanan +3
Recent advances in text-to-speech (TTS) systems, particularly those with voice cloning capabilities, have made voice impersonation readily accessible, raising ethical and legal con…
Differentially Private Parameter-Efficient Fine-tuning for Large ASR Models
Hongbin Liu, Lun Wang, Om Thakkar +2
Large ASR models can inadvertently leak sensitive information, which can be mitigated by formal privacy measures like differential privacy (DP). However, traditional DP training is…