Ji-Xiang's picture

Ji-Xiang

Ji-Xiang

·

AI & ML interests

None yet

Recent Activity

liked a model 3 days ago

moonshotai/Kimi-Linear-48B-A3B-Instruct

upvoted a collection 7 days ago

upvoted an article 12 days ago

Supercharge your OCR Pipelines with Open Models

View all activity

Organizations

upvoted a collection 7 days ago

MiniMax-M1

MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model. • 6 items • Updated 15 days ago • 114

upvoted an article 12 days ago

Article

Supercharge your OCR Pipelines with Open Models

15 days ago

• 221

upvoted 2 collections about 1 month ago

Ming-V2

9 items • Updated 6 days ago • 29

DeepSeek-V3.2

2 items • Updated Sep 29 • 441

upvoted 2 collections about 2 months ago

Granite Docling

5 items • Updated 5 days ago • 58

PP-OCRv5

PP-OCRv5 is the latest text recognition solution, supporting Simplified Chinese, Chinese Pinyin, Traditional Chinese, English, and Japanese • 13 items • Updated Sep 15 • 48

upvoted a collection 2 months ago

EmbeddingGemma

3 items • Updated Sep 11 • 94

upvoted 3 collections 3 months ago

DeepSeek-V3.1

4 items • Updated Sep 22 • 244

DINOv3

DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104 • 13 items • Updated Aug 21 • 367

gpt-oss

Open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases. • 2 items • Updated Aug 7 • 374

upvoted 2 collections 4 months ago

Kimi-K2

Moonshot's MoE LLMs with 1 trillion parameters, exceptional on agentic intellegence • 3 items • Updated 6 days ago • 128

Gemma 3n

4 items • Updated Jul 10 • 235

upvoted a collection 5 months ago

V-JEPA 2

A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of https://ai.meta.com/blog/v-jepa-yann • 8 items • Updated Jun 13 • 167

upvoted an article 5 months ago

Article

SmolVLA: Efficient Vision-Language-Action Model trained on Lerobot Community Data

Jun 3

• 272

upvoted a collection 5 months ago

Common Pile v0.1

All resources related to Common Pile v0.1, an 8TB dataset of public domain and openly licensed text • 4 items • Updated Jun 6 • 33

upvoted an article 5 months ago

Article

The Common Pile v0.1

By

and 2 others •

Jun 6

• 51

upvoted a collection 5 months ago

Qwen3-Reranker

3 items • Updated Jul 21 • 64

upvoted a paper 5 months ago

SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond

Paper • 2505.19641 • Published May 26 • 67

upvoted 2 collections 6 months ago

🧠 Traditional Chinese Reasoning Datasets

A curated collection of datasets designed to evaluate and train reasoning capabilities in Traditional Chinese across various domains. • 3 items • Updated 23 days ago • 8

🏠 ParScale-1.8B

Base models trained on 1T high-quality tokens, demonstrating strong competitiveness among existing SOTA small models (<2B). • 4 items • Updated May 17 • 2