Ji-Xiang's picture

Ji-Xiang

Ji-Xiang

·

AI & ML interests

None yet

Recent Activity

updated a collection 8 days ago

liked a model 8 days ago

microsoft/Phi-4-reasoning-vision-15B

liked a model 9 days ago

Qwen/Qwen3.5-35B-A3B

View all activity

Organizations

upvoted a collection 9 days ago

Qwen3.5

21 items • Updated 4 days ago • 1.14k

upvoted a collection 22 days ago

Qwen3-TTS

7 items • Updated Jan 22 • 323

upvoted an article about 1 month ago

Article

M2.1: Multilingual and Multi-Task Coding with Strong Generalization

Jan 5

•

40

upvoted 2 collections about 1 month ago

Qwen3-Coder-Next

4 items • Updated Feb 3 • 105

Qwen3-ASR

4 items • Updated Jan 29 • 53

upvoted an article about 2 months ago

Article

SigLIP 2: A better multilingual vision language encoder

+1

Feb 21, 2025

•

206

upvoted 2 collections 3 months ago

VibeVoice

Frontier Text-to-Speech Models https://microsoft.github.io/VibeVoice/ • 8 items • Updated 11 days ago • 211

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. • 2 items • Updated 11 days ago • 46

upvoted an article 3 months ago

Article

We Got Claude to Fine-Tune an Open Source LLM

Dec 4, 2025

•

608

upvoted a collection 4 months ago

MiniMax-M1

MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model. • 6 items • Updated 28 days ago • 118

upvoted an article 5 months ago

Article

Supercharge your OCR Pipelines with Open Models

+5

Oct 21, 2025

•

307

upvoted 2 collections 5 months ago

Ming-V2

Ming is the multi-modal series of any-to-any models developed by Ant Ling team. • 14 items • Updated 6 days ago • 35

DeepSeek-V3.2

4 items • Updated Dec 1, 2025 • 531

upvoted 3 collections 6 months ago

Granite Docling

4 items • Updated 11 days ago • 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, 2025 • 52

EmbeddingGemma

3 items • Updated about 18 hours ago • 114

upvoted 3 collections 7 months ago

DeepSeek-V3.1

3 items • Updated 11 days ago • 261

DINOv3

DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104 • 15 items • Updated 2 days ago • 533

gpt-oss

Open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases. • 2 items • Updated Aug 7, 2025 • 420

upvoted a collection 8 months ago

Kimi-K2

Moonshot's MoE LLMs with 1 trillion parameters, exceptional on agentic intellegence • 5 items • Updated Jan 27 • 172