Ji-Xiang's picture

Ji-Xiang

Ji-Xiang

·

AI & ML interests

None yet

Recent Activity

updated a collection 16 days ago

text-to-speech (TTS)

liked a model 16 days ago

microsoft/VibeVoice-1.5B

upvoted a collection 16 days ago

View all activity

Organizations

upvoted 2 collections 16 days ago

VibeVoice

Frontier Text-to-Speech Models https://microsoft.github.io/VibeVoice/ • 8 items • Updated 22 days ago • 180

Devstral 2

A couple of agentic LLMs for software engineering tasks, excelling at using tools to explore codebases, edit multiple files, and power SWE Agents. • 3 items • Updated 17 days ago • 37

upvoted an article 20 days ago

Article

We Got Claude to Fine-Tune an Open Source LLM

23 days ago

•

535

upvoted a collection about 2 months ago

MiniMax-M1

MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model. • 6 items • Updated Oct 21 • 119

upvoted an article 2 months ago

Article

Supercharge your OCR Pipelines with Open Models

+5

Oct 21

•

282

upvoted 4 collections 3 months ago

Ming-V2

10 items • Updated 2 days ago • 30

DeepSeek-V3.2

4 items • Updated 25 days ago • 510

Granite Docling

5 items • Updated Nov 17 • 60

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 • 50

upvoted 3 collections 4 months ago

EmbeddingGemma

3 items • Updated Sep 11 • 104

DeepSeek-V3.1

4 items • Updated 29 days ago • 256

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 • 429

upvoted a collection 5 months ago

gpt-oss

Open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases. • 2 items • Updated Aug 7 • 393

upvoted 2 collections 6 months ago

Kimi-K2

Moonshot's MoE LLMs with 1 trillion parameters, exceptional on agentic intellegence • 5 items • Updated Nov 14 • 162

Gemma 3n

4 items • Updated Jul 10 • 252

upvoted a collection 7 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 • 174

upvoted an article 7 months ago

Article

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

+7

Jun 3

•

299

upvoted a collection 7 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 • 39

upvoted an article 7 months ago

Article

The Common Pile v0.1

Jun 6

•

52

upvoted a collection 7 months ago

Qwen3-Reranker

3 items • Updated Jul 21 • 64