Zhuchenyang Liu

Ryenhails

·

AI & ML interests

None yet

Recent Activity

authored a paper 7 minutes ago

Evidence Attribution in Visual Document Understanding without Coordinates or Region Labels

updated a model about 6 hours ago

Ryenhails/quote-and-retrieve-8b-grpo

published a model about 7 hours ago

Ryenhails/quote-and-retrieve-8b-grpo

View all activity

Organizations

Articles 1

Article

3

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

Papers 6

arxiv:2607.24651

arxiv:2601.20107

arxiv:2604.21668

arxiv:2604.00913

models 4

Ryenhails/quote-and-retrieve-8b-grpo

Image-Text-to-Text • 9B • Updated about 6 hours ago

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

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

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

Automatic Speech Recognition • 0.6B • Updated Nov 30, 2024 • 1

Ryenhails/t5-fine-tuned-model

60.5M • Updated Nov 28, 2024 • 2

datasets 2

Ryenhails/quote-and-retrieve-eval

Viewer • Updated about 6 hours ago • 719

Ryenhails/ikea-bench

Preview • Updated Apr 2 • 55