Zhuchenyang Liu PRO

Ryenhails's activity

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

upvoted an article 1 day ago

view article

Article

Two Pure-Vision Pipelines at the Top of ViDoRe V3

• 

Ryenhails

•

1 day ago

• 6

upvoted a paper 4 days ago

Multimodal Reranking Is a System One Decision

Paper • 2610.28435 • Published 5 days ago • 8

upvoted an article 10 days ago

view article

Article

autotrust/JEV-27B-VL: a decision model that learned to see without a single image of training

• 

autotrust

•

25 days ago

• 43

upvoted a collection 10 days ago

Encoder comparison after equivalent retrieval fine-tuning

Collection

ModernBERT, Ettin and UltraBERT: 54 retrieval models, frozen data and results. Validation-selected models first. Matched training, one seed. • 59 items • Updated 10 days ago • 4

upvoted a paper 10 days ago

GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives

Paper • 2609.39601 • Published 25 days ago • 150

upvoted an article 10 days ago

view article

Article

One Decision Model Instead of a Ranking Team: Short-Video and News Recommendation with autotrust/JEV-27B-VL

• 

autotrust

•

12 days ago

• 6

upvoted a paper 10 days ago

DAEDALUS: Bootstrapping Agent Memory from Self-Generated Tasks

Paper • 2610.08048 • Published 19 days ago • 18

upvoted an article 12 days ago

view article

Article

A framework and leaderboard for Retrieval Pipelines evaluation on ViDoRe v3

• 

antoineedy

•

Feb 27

• 14

upvoted a paper 17 days ago

Inverting Multi-Vector Visual Document Indices

Paper • 2610.09920 • Published 18 days ago • 28

upvoted a paper 26 days ago

ColNanoVDR: Document-Free Query Distillation for Multi-Vector Visual Document Retrieval via Optimal Transport

Paper • 2609.34899 • Published 27 days ago • 7

upvoted a paper about 1 month ago

DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression

Paper • 2609.19969 • Published Sep 17 • 235

upvoted an article about 2 months ago

view article

Article

NeoMME: an efficient Multimodal-native and Multilingual Encoder

• 

Hcompany

•

Sep 3

• 122

upvoted 2 papers 2 months ago

MonkeyOCRv2: A Visual-Text Foundation Model for Document AI

Paper • 2607.11562 • Published Jul 13 • 39

DistilVDR: A Compact End-to-End Visual Document Retriever via Dual-Student Distillation

Paper • 2608.10636 • Published Aug 11 • 12

upvoted 3 papers 3 months ago

How to Train Your Long-Context Visual Document Model

Paper • 2602.15257 • Published Feb 16 • 2

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published Jul 27 • 537

Evidence Attribution in Visual Document Understanding without Coordinates or Region Labels

Paper • 2607.24651 • Published Jul 27 • 4

upvoted a paper 4 months ago

Unlimited OCR Works

Paper • 2606.23050 • Published Jun 22 • 97

upvoted an article 5 months ago

view article

Article

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

• 

QuentinJG

•

Nov 5, 2025

• 70

upvoted a paper 5 months ago

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

Paper • 2605.20177 • Published May 19 • 8