activity
20222024
most citedSteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF

3 citations · 4 across the 7 of their papers we have counts for

collaborators

7 papers

math.AP2024

Nonexistence of invariant nodal line and improved restriction bounds for Neumann data on negatively curved surface

Xianchao Wu, Lan Zhang

The problem of obtaining the lower bounds on the restriction of Laplacian eigenfunctions to hypersurfaces inside a compact Riemannian manifold is challenging and has been a…

math.AP2024

The restriction bounds for Neumann data on surface

Xianchao Wu

Let be a sequence of -normalized Laplacian eigenfunctions on a compact two-dimensional smooth Riemanniann manifold . We seek to get an restriction bound…

cs.CL20233 cited

SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF

Yi Dong, Zhilin Wang, Makesh Narsimhan Sreedhar +2

Model alignment with human preferences is an essential step in making Large Language Models (LLMs) helpful and consistent with human values. It typically consists of supervised fin…

cs.CL2023

Duplex Diffusion Models Improve Speech-to-Speech Translation

Xianchao Wu

Speech-to-speech translation is a typical sequence-to-sequence learning task that naturally has two directions. How to effectively leverage bidirectional supervision signals to pro…

cs.CL2023

Enhancing Unsupervised Speech Recognition with Diffusion GANs

Xianchao Wu

We enhance the vanilla adversarial training method for unsupervised Automatic Speech Recognition (ASR) by a diffusion-GAN. Our model (1) injects instance noises of various intensit…

cs.CL20221 cited

Attention Enhanced Citrinet for Speech Recognition

Xianchao Wu

Citrinet is an end-to-end convolutional Connectionist Temporal Classification (CTC) based automatic speech recognition (ASR) model. To capture local and global contextual informati…