Bowen Shi

Affiliations

Shanghai Jiao Tong University

papers

557

total citations

papers (12)

Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale

NEURIPS 2023arXiv

443

citations

u-HuBERT: Unified Mixed-Modal Speech Pretraining And Zero-Shot Transfer to Unlabeled Modality

NEURIPS 2022arXiv

citations

METEOR: Multi-Encoder Collaborative Token Pruning for Efficient Vision Language Models

ICCV 2025arXiv

citations

ReVISE: Self-Supervised Speech Resynthesis With Visual Input for Universal and Generalized Speech Regeneration

CVPR 2023

citations

Adapting Shortcut With Normalizing Flow: An Efficient Tuning Framework for Visual Recognition

CVPR 2023

citations

Scaling Speech Technology to 1,000+ Languages

ICML 2024

citations

Bootstrap AutoEncoders With Contrastive Paradigm for Self-supervised Gaze Estimation

ICML 2024

citations

A Transformer-Based Decoder for Semantic Segmentation with Multi-level Context Mining

ECCV 2022

citations

Bowen Shi

Affiliations

papers (12)

Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale

u-HuBERT: Unified Mixed-Modal Speech Pretraining And Zero-Shot Transfer to Unlabeled Modality

Fingerspelling Detection in American Sign Language

AiluRus: A Scalable ViT Framework for Dense Prediction

MusicFlow: Cascaded Flow Matching for Text Guided Music Generation

Hybrid Distillation: Connecting Masked Autoencoders with Contrastive Learners

METEOR: Multi-Encoder Collaborative Token Pruning for Efficient Vision Language Models

ReVISE: Self-Supervised Speech Resynthesis With Visual Input for Universal and Generalized Speech Regeneration

Adapting Shortcut With Normalizing Flow: An Efficient Tuning Framework for Visual Recognition

Scaling Speech Technology to 1,000+ Languages

Bootstrap AutoEncoders With Contrastive Paradigm for Self-supervised Gaze Estimation

A Transformer-Based Decoder for Semantic Segmentation with Multi-level Context Mining

papers (12)

Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale

u-HuBERT: Unified Mixed-Modal Speech Pretraining And Zero-Shot Transfer to Unlabeled Modality

Fingerspelling Detection in American Sign Language

AiluRus: A Scalable ViT Framework for Dense Prediction

MusicFlow: Cascaded Flow Matching for Text Guided Music Generation

Hybrid Distillation: Connecting Masked Autoencoders with Contrastive Learners

METEOR: Multi-Encoder Collaborative Token Pruning for Efficient Vision Language Models

ReVISE: Self-Supervised Speech Resynthesis With Visual Input for Universal and Generalized Speech Regeneration

Adapting Shortcut With Normalizing Flow: An Efficient Tuning Framework for Visual Recognition

Scaling Speech Technology to 1,000+ Languages

Bootstrap AutoEncoders With Contrastive Paradigm for Self-supervised Gaze Estimation

A Transformer-Based Decoder for Semantic Segmentation with Multi-level Context Mining