Kaicheng Yang

Kaichengalex's activity

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

updated a collection 9 days ago

SFT Dataset

Collection

10 items • Updated 9 days ago

updated 2 collections 26 days ago

SFT Dataset

Collection

10 items • Updated 9 days ago

Doc Data

Collection

2 items • Updated 26 days ago

updated a collection 28 days ago

Vision-Language Dataset

Collection

7 items • Updated 28 days ago

liked a model about 1 month ago

uer/gpt2-chinese-cluecorpussmall

Text Generation • Updated Oct 17, 2023 • 17.4k • 257

updated a collection about 1 month ago

Vision-Language Dataset

Collection

7 items • Updated 28 days ago

liked a Space about 1 month ago

Running

Agents

1

MMEB Leaderboard

📊

1

The massive multimodal embedding benchmark

upvoted 3 papers about 2 months ago

InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning

Paper • 2606.12195 • Published Jun 10 • 23

Visual Para-Thinker++: A Single-Policy Multi-Agent Framework for Visual Reasoning

Paper • 2606.09290 • Published Jun 8 • 8

SG-OPD: Sign-Gated On-Policy Distillation via Sign-Consistency Gating and Phased Teacher Sampling

Paper • 2606.09304 • Published Jun 8 • 6

liked a dataset about 2 months ago

nvidia/NitroGen

Updated Jan 12 • 1.12k • 220

updated a collection about 2 months ago

VideoDataset

Collection

3 items • Updated Jun 6

updated a collection 2 months ago

Vision-Language Dataset

Collection

7 items • Updated 28 days ago

upvoted an article 2 months ago

view article

Article

Codex 正在推动 AI 模型的开源与训练流程

• 
• 

burtenshaw, evalstate

•

Dec 11, 2025

• 17

upvoted a paper 2 months ago

From Pixels to Words -- Towards Native One-Vision Models at Scale

Paper • 2605.28820 • Published May 27 • 76

updated a collection 3 months ago

VideoDataset

Collection

3 items • Updated Jun 6

liked a dataset 3 months ago

mvp-lab/LLaVA-OneVision-2-Data

Viewer • Updated 15 days ago • 24 • 146k • 32

liked a Space 3 months ago

Running on Zero

Agents

9

Paddleocr 3.5 Transformers Demo

👁

9

Run OCR & Doc-Parsing with PaddleOCR 3.5 and Transforformers