Chuanming Liu

Chuanming's activity

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

upvoted an article about 17 hours ago

view article

Article

SigLIP 2: A better multilingual vision language encoder

• 
• 
• +1

Feb 21, 2025

•

197

upvoted an article 6 days ago

view article

Article

Scaling Real-Time Voice Agents with Cache-Aware Streaming ASR

• 

30 days ago

•

76

upvoted an article 20 days ago

view article

Article

Open Responses: What you need to know

• 
• 
• +2

21 days ago

•

103

upvoted an article about 1 month ago

view article

Article

Tokenization in Transformers v5: Simpler, Clearer, and More Modular

• 
• 
• +4

Dec 18, 2025

•

119

upvoted a paper about 2 months ago

Stabilizing Reinforcement Learning with LLMs: Formulation and Practices

Paper • 2512.01374 • Published Dec 1, 2025 • 104

upvoted 2 articles 3 months ago

view article

Article

Fine-Tune Whisper For Multilingual ASR with 🤗 Transformers

• 

Nov 3, 2022

•

350

view article

Article

Supercharge your OCR Pipelines with Open Models

• 
• 
• +5

Oct 21, 2025

•

301

upvoted 2 papers 4 months ago

MiniMax-Speech: Intrinsic Zero-Shot Text-to-Speech with a Learnable Speaker Encoder

Paper • 2505.07916 • Published May 12, 2025 • 134

Finite Scalar Quantization Enables Redundant and Transmission-Robust Neural Audio Compression at Low Bit-rates

Paper • 2509.09550 • Published Sep 11, 2025 • 3

upvoted 2 collections 4 months ago

Qwen3Guard

Collection

7 items • Updated Dec 31, 2025 • 62

Qwen3-Omni

Collection

6 items • Updated Dec 31, 2025 • 182

upvoted an article 5 months ago

view article

Article

Understanding Vector Quantization in VQ-VAE

• 

Aug 28, 2024

•

53

upvoted a paper 5 months ago

Group Sequence Policy Optimization

Paper • 2507.18071 • Published Jul 24, 2025 • 316

upvoted an article 5 months ago

view article

Article

From GRPO to DAPO and GSPO: What, Why, and How

• 

Aug 9, 2025

•

81

upvoted 2 collections 5 months ago

PP-StructureV3

Collection

PP-StructureV3 is a SOTA document parsing solution on OmniDocBench, supporting the conversion of PDFs and do cument images to Markdown and JSON. • 17 items • Updated Sep 15, 2025 • 12

PP-OCRv5

Collection

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

upvoted a paper 5 months ago

Step-Audio 2 Technical Report

Paper • 2507.16632 • Published Jul 22, 2025 • 73

upvoted a collection 5 months ago

Marvis-TTS-250m-v0.1

Collection

5 items • Updated Aug 26, 2025 • 26

upvoted 2 collections 6 months ago

AFM-Datasets

Collection

Training datasets for OPPO Personal AI Lab’s family of Agent Foundation Models. • 6 items • Updated about 15 hours ago • 6

AFM-Models

Collection

Models for OPPO Personal AI Lab’s family of Agent Foundation Models. • 13 items • Updated about 15 hours ago • 17