Haoran Wei

HaoranWei's activity

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

upvoted 3 papers 1 day ago

MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning

Paper • 2601.21468 • Published 9 days ago • 20

CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding

Paper • 2602.01785 • Published 5 days ago • 91

Length-Unbiased Sequence Policy Optimization: Revealing and Controlling Response Length Variation in RLVR

Paper • 2602.05261 • Published 3 days ago • 45

upvoted a paper 2 days ago

ReGuLaR: Variational Latent Reasoning Guided by Rendered Chain-of-Thought

Paper • 2601.23184 • Published 8 days ago • 34

upvoted a collection 5 days ago

DeepSeek-OCR

Collection

2 items • Updated 5 days ago • 13

upvoted a paper 9 days ago

DeepSeek-OCR 2: Visual Causal Flow

Paper • 2601.20552 • Published 10 days ago • 54

upvoted a paper 22 days ago

STEP3-VL-10B Technical Report

Paper • 2601.09668 • Published 24 days ago • 193

upvoted a paper 25 days ago

BabyVision: Visual Reasoning Beyond Language

Paper • 2601.06521 • Published 28 days ago • 195

upvoted a paper 26 days ago

AgentOCR: Reimagining Agent History via Optical Self-Compression

Paper • 2601.04786 • Published about 1 month ago • 29

upvoted a paper 2 months ago

DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

Paper • 2512.02556 • Published Dec 2, 2025 • 255

upvoted a paper 4 months ago

DeepSeek-OCR: Contexts Optical Compression

Paper • 2510.18234 • Published Oct 21, 2025 • 92

upvoted a paper 6 months ago

NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale

Paper • 2508.10711 • Published Aug 14, 2025 • 145

upvoted 2 collections 6 months ago

NextStep-1

Collection

9 items • Updated Dec 24, 2025 • 32

Step3

Collection

2 items • Updated Jul 31, 2025 • 21

upvoted a paper about 1 year ago

Slow Perception: Let's Perceive Geometric Figures Step-by-step

Paper • 2412.20631 • Published Dec 30, 2024 • 15

upvoted a collection about 1 year ago

Document AI

Collection

All the papers that can fundementally help in creating a true open-source processing pipeline. • 1 item • Updated Nov 11, 2024 • 1

upvoted a paper about 1 year ago

Focus Anywhere for Fine-grained Multi-page Document Understanding

Paper • 2405.14295 • Published May 23, 2024 • 1

upvoted a collection about 1 year ago

PixMo

Collection

A set of vision-language datasets built by Ai2 and used to train the Molmo family of models. Read more at https://molmo.allenai.org/blog • 10 items • Updated Dec 23, 2025 • 85

upvoted 2 papers over 1 year ago

General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

Paper • 2409.01704 • Published Sep 3, 2024 • 83

DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation

Paper • 2406.16855 • Published Jun 24, 2024 • 57