Zobrazeno 1 - 10
of 4 703
pro vyhledávání: '"Hu,Ke"'
NeKo: Toward Post Recognition Generative Correction Large Language Models with Task-Oriented Experts
Autor:
Lin, Yen-Ting, Yang, Chao-Han Huck, Chen, Zhehuai, Zelasko, Piotr, Yang, Xuesong, Chen, Zih-Ching, Puvvada, Krishna C, Fu, Szu-Wei, Hu, Ke, Chiu, Jun Wei, Balam, Jagadeesh, Ginsburg, Boris, Wang, Yu-Chiang Frank
Construction of a general-purpose post-recognition error corrector poses a crucial question: how can we most effectively train a model on a large mixture of domain datasets? The answer would lie in learning dataset-specific features and digesting the
Externí odkaz:
http://arxiv.org/abs/2411.05945
Autor:
Peng, Yifan, Puvvada, Krishna C., Chen, Zhehuai, Zelasko, Piotr, Huang, He, Dhawan, Kunal, Hu, Ke, Watanabe, Shinji, Balam, Jagadeesh, Ginsburg, Boris
Recent studies have augmented large language models (LLMs) with speech capabilities, leading to the development of speech language models (SpeechLMs). Earlier SpeechLMs focused on single-turn speech-based question answering (QA), where user input com
Externí odkaz:
http://arxiv.org/abs/2410.17485
Autor:
Żelasko, Piotr, Chen, Zhehuai, Wang, Mengru, Galvez, Daniel, Hrinchuk, Oleksii, Ding, Shuoyang, Hu, Ke, Balam, Jagadeesh, Lavrukhin, Vitaly, Ginsburg, Boris
A rising interest in the modality extension of foundation language models warrants discussion on the most effective, and efficient, multimodal training approach. This work focuses on neural machine translation (NMT) and proposes a joint multimodal tr
Externí odkaz:
http://arxiv.org/abs/2409.13523
Autor:
Hu, Ke, Chen, Zhehuai, Yang, Chao-Han Huck, Żelasko, Piotr, Hrinchuk, Oleksii, Lavrukhin, Vitaly, Balam, Jagadeesh, Ginsburg, Boris
Large language models (LLMs) have demonstrated remarkable advancements in language understanding and generation. Building on the success of text-based LLMs, recent research has adapted these models to use speech embeddings for prompting, resulting in
Externí odkaz:
http://arxiv.org/abs/2409.11538
Principal component analysis (PCA) is a classical feature extraction method, but it may be adversely affected by outliers, resulting in inaccurate learning of the projection matrix. This paper proposes a robust method to estimate both the data mean a
Externí odkaz:
http://arxiv.org/abs/2408.12366
Autor:
Ding, Shutong, Hu, Ke, Zhang, Zhenhao, Ren, Kan, Zhang, Weinan, Yu, Jingyi, Wang, Jingya, Shi, Ye
Diffusion models have garnered widespread attention in Reinforcement Learning (RL) for their powerful expressiveness and multimodality. It has been verified that utilizing diffusion policies can significantly improve the performance of RL algorithms
Externí odkaz:
http://arxiv.org/abs/2405.16173
Autor:
Ni, Bolin, Zhao, Hongbo, Zhang, Chenghao, Hu, Ke, Meng, Gaofeng, Zhang, Zhaoxiang, Xiang, Shiming
Continual learning (CL) aims to empower models to learn new tasks without forgetting previously acquired knowledge. Most prior works concentrate on the techniques of architectures, replay data, regularization, \etc. However, the category name of each
Externí odkaz:
http://arxiv.org/abs/2403.16124
Autor:
Hu, Ke, Yi, Longqing
We propose utilizing a polarization-tailored high-power laser pulse to extract and accelerate electrons from the edge of a solid foil target to produce isolated attosecond electron bunches. The laser pulse consists of two orthogonally-polarized compo
Externí odkaz:
http://arxiv.org/abs/2403.10017
Autor:
Huang, W. Ronny, Allauzen, Cyril, Chen, Tongzhou, Gupta, Kilol, Hu, Ke, Qin, James, Zhang, Yu, Wang, Yongqiang, Chang, Shuo-Yiin, Sainath, Tara N.
In the era of large models, the autoregressive nature of decoding often results in latency serving as a significant bottleneck. We propose a non-autoregressive LM-fused ASR system that effectively leverages the parallelization capabilities of acceler
Externí odkaz:
http://arxiv.org/abs/2401.12789
In the field of federated learning, addressing non-independent and identically distributed (non-i.i.d.) data remains a quintessential challenge for improving global model performance. This work introduces the Feature Norm Regularized Federated Learni
Externí odkaz:
http://arxiv.org/abs/2312.06951