SeeFun's picture

Building on HF

SeeFun

AI4Industry

·

seefun

AI & ML interests

None yet

Recent Activity

liked a model 3 days ago

opendatalab/MinerU2.5-Pro-2604-1.2B

liked a model 3 days ago

infly/Infinity-Parser2-Pro

liked a dataset 4 days ago

MMTR-Bench/MMTR-Bench-Dataset

View all activity

Organizations

upvoted a collection 26 days ago

Nemotron-Cascade 2

Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation • 4 items • Updated 2 days ago • 48

upvoted a paper about 2 months ago

OmniScience: A Large-scale Multi-modal Dataset for Scientific Image Understanding

Paper • 2602.13758 • Published Feb 14 • 6

upvoted 2 articles 3 months ago

Article

流式数据集：效率提升 100 倍

+3

Oct 27, 2025

•

7

Article

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

Jan 19

•

91

upvoted a collection 3 months ago

TranslateGemma

3 items • Updated Mar 12 • 234

upvoted 2 papers 4 months ago

Uni-Parser Technical Report

Paper • 2512.15098 • Published Dec 17, 2025 • 2

RxnBench: A Multimodal Benchmark for Evaluating Large Language Models on Chemical Reaction Understanding from Scientific Literature

Paper • 2512.23565 • Published Dec 29, 2025 • 1

upvoted a collection 4 months ago

RxnBench

Chemical Reaction VQA Benchmark • 2 items • Updated Jan 13 • 1

upvoted a paper 5 months ago

olmOCR 2: Unit Test Rewards for Document OCR

Paper • 2510.19817 • Published Oct 22, 2025 • 16

upvoted a paper 7 months ago

SAIL-VL2 Technical Report

Paper • 2509.14033 • Published Sep 17, 2025 • 44

upvoted 2 collections 7 months ago

MolDet

Molecule Image Detection • 4 items • Updated about 1 month ago • 2

MolParser

Molecule Image Recognition • 2 items • Updated about 1 month ago • 1

upvoted an article 8 months ago

Article

NVIDIA Releases 3 Million Sample Dataset for OCR, Visual Question Answering, and Captioning Tasks

Aug 11, 2025

•

76

upvoted a paper 11 months ago

SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion

Paper • 2503.11576 • Published Mar 14, 2025 • 156

upvoted a collection 12 months ago

SigLIP 2

OpenCLIP and timm SigLIP 2 models • 47 items • Updated Sep 19, 2025 • 27

upvoted 3 articles about 1 year ago

Article

SmolVLM2: Bringing Video Understanding to Every Device

+5

Feb 20, 2025

•

336

Article

Open-source DeepResearch – Freeing our search agents

+3

Feb 4, 2025

•

1.32k

Article

Timm ❤️ Transformers: Use any timm model with transformers

+3

Jan 16, 2025

•

55

upvoted a paper over 1 year ago

MolParser: End-to-end Visual Recognition of Molecule Structures in the Wild

Paper • 2411.11098 • Published Nov 17, 2024 • 1

upvoted a collection over 1 year ago

Qwen2-VL

Vision-language model series based on Qwen2 • 15 items • Updated Mar 2 • 231