Zhuchenyang Liu

Ryenhails's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted an article 4 days ago

view article

Article

ViDoRe V3: a comprehensive evaluation of retrieval for enterprise use-cases

• 

QuentinJG

•

Nov 5, 2025

• 66

upvoted a paper 13 days ago

From Seeing to Thinking: Decoupling Perception and Reasoning Improves Post-Training of Vision-Language Models

Paper • 2605.20177 • Published 20 days ago • 10

upvoted a paper about 1 month ago

Encoder-Free Human Motion Understanding via Structured Motion Descriptions

Paper • 2604.21668 • Published Apr 23 • 3

upvoted a paper about 2 months ago

Multimodal OCR: Parse Anything from Documents

Paper • 2603.13032 • Published Mar 13 • 45

upvoted 3 papers 2 months ago

Steerable Visual Representations

Paper • 2604.02327 • Published Apr 2 • 56

Benchmarking and Mechanistic Analysis of Vision-Language Models for Cross-Depiction Assembly Instruction Alignment

Paper • 2604.00913 • Published Apr 1 • 4

LongCat-Next: Lexicalizing Modalities as Discrete Tokens

Paper • 2603.27538 • Published Mar 29 • 147

upvoted an article 2 months ago

view article

Article

Qwen3.5: Nobody Agrees on Attention Anymore

• 

mlabonne

•

Feb 17

• 26

upvoted a paper 3 months ago

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

Paper • 2603.12824 • Published Mar 13 • 5

upvoted an article 3 months ago

view article

Article

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

• 

Ryenhails

•

Mar 16

• 3

upvoted 2 articles 5 months ago

view article

Article

LightOnOCR-2-1B: a lightweight high-performance end-to-end OCR model family

• 

lightonai

•

Jan 19

• 95

view article

Article

How We Built a Semantic Highlight Model To Save Token Cost for RAG

• 

zilliz

•

Jan 15

• 67

upvoted a paper 8 months ago

UniGenBench++: A Unified Semantic Evaluation Benchmark for Text-to-Image Generation

Paper • 2510.18701 • Published Oct 21, 2025 • 68