Bowen Shi

13

Papers

10

Total Citations

1

Affiliations

Affiliations

Shanghai Jiao Tong University

Papers (13)

Hybrid Distillation: Connecting Masked Autoencoders with Contrastive Learners

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

Bootstrap AutoEncoders With Contrastive Paradigm for Self-supervised Gaze Estimation

MusicFlow: Cascaded Flow Matching for Text Guided Music Generation

Fingerspelling Detection in American Sign Language

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

Fingerspelling Recognition in the Wild With Iterative Visual Attention

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

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

Scaling Speech Technology to 1,000+ Languages

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

Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale

AiluRus: A Scalable ViT Framework for Dense Prediction