Zhuchenyang Liu's picture

Zhuchenyang Liu

Ryenhails

·

AI & ML interests

None yet

Recent Activity

upvoted a paper about 21 hours ago

NanoVDR: Distilling a 2B Vision-Language Retriever into a 70M Text-Only Encoder for Visual Document Retrieval

updated a dataset about 22 hours ago

nanovdr/NanoVDR-Train

authored a paper 1 day ago

NanoVDR: Distilling a 2B Vision-Language Retriever into a 70M Text-Only Encoder for Visual Document Retrieval

View all activity

Organizations

Articles 1

Article

2

NanoVDR: A 70M Text-Only Model That Retrieves Visual Documents as Well as a 2B VLM

Papers 3

arxiv:2603.12824

arxiv:2603.09930

arxiv:2601.20107

models 3

Ryenhails/w2v-bert-2.0-geo-all-train_withSpec

Automatic Speech Recognition • 0.6B • Updated Dec 4, 2024

Ryenhails/w2v-bert-2.0-geo-all-train_noregularization

Automatic Speech Recognition • 0.6B • Updated Nov 30, 2024

Ryenhails/t5-fine-tuned-model

60.5M • Updated Nov 28, 2024

datasets 0

None public yet