no code implementations • 9 Oct 2023 • Yi Dong, Zhilin Wang, Makesh Narsimhan Sreedhar, Xianchao Wu, Oleksii Kuchaiev
Model alignment with human preferences is an essential step in making Large Language Models (LLMs) helpful and consistent with human values.
no code implementations • 4 Oct 2023 • Peng Xu, Wei Ping, Xianchao Wu, Lawrence McAfee, Chen Zhu, Zihan Liu, Sandeep Subramanian, Evelina Bakhturina, Mohammad Shoeybi, Bryan Catanzaro
Perhaps surprisingly, we find that LLM with 4K context window using simple retrieval-augmentation at generation can achieve comparable performance to finetuned LLM with 16K context window via positional interpolation on long context tasks, while taking much less computation.
no code implementations • 22 May 2023 • Xianchao Wu
Speech-to-speech translation is a typical sequence-to-sequence learning task that naturally has two directions.
no code implementations • 23 Mar 2023 • Xianchao Wu
We enhance the vanilla adversarial training method for unsupervised Automatic Speech Recognition (ASR) by a diffusion-GAN.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • CAI (COLING) 2022 • Xianchao Wu
In this paper, we focus on enhancing the creative painting ability of current LDMs in two directions, textual condition extension and model retraining with Wikiart dataset.
no code implementations • 1 Sep 2022 • Xianchao Wu
Citrinet is an end-to-end convolutional Connectionist Temporal Classification (CTC) based automatic speech recognition (ASR) model.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
1 code implementation • 1 Sep 2022 • Xianchao Wu
A deep normalization strategy is utilized when performing residual connections to ensure our training of hundred-level Conformer blocks.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 1 Jan 2021 • Xianchao Wu
We propose two linguistic verifiers for span-extraction style machine reading comprehension to respectively tackle two challenges: how to evaluate the syntactic completeness of predicted answers and how to utilize the rich context of long documents.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Xianchao Wu
It is reported that financial news, especially financial events expressed in news, provide information to investors' long/short decisions and influence the movements of stock markets.
no code implementations • EMNLP 2018 • Huang Hu, Xianchao Wu, Bingfeng Luo, Chongyang Tao, Can Xu, Wei Wu, Zhan Chen
The 20 Questions (Q20) game is a well known game which encourages deductive reasoning and creativity.
no code implementations • NAACL 2018 • Xianchao Wu, Ander Mart{\'\i}nez, Momo Klyen
In this paper, we propose a generalizable dialog generation approach that adapts multi-turn reasoning, one recent advancement in the field of document comprehension, to generate responses ({``}answers{''}) by taking current conversation session context as a {``}document{''} and current query as a {``}question{''}.