Donghua Yu

yhzx233's activity

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

authored 2 papers about 15 hours ago

MOSS-Speech: Towards True Speech-to-Speech Models Without Text Guidance

Paper • 2510.00499 • Published Oct 1, 2025 • 19

MOSS Transcribe Diarize: Accurate Transcription with Speaker Diarization

Paper • 2601.01554 • Published 5 days ago • 50

updated a Space 3 days ago

Running

Featured

34

MOSS Transcribe Diarize

🏢

34

Transcribe audio/video files with speaker identification

liked a Space 3 days ago

Running

Featured

34

MOSS Transcribe Diarize

🏢

34

Transcribe audio/video files with speaker identification

upvoted a paper 3 days ago

MOSS Transcribe Diarize: Accurate Transcription with Speaker Diarization

Paper • 2601.01554 • Published 5 days ago • 50

updated a Space 3 months ago

Running on Zero

39

MOSS TTSD

📉

39

MOSS-TTSD: Text to Spoken Dialogue Generation

liked a Space 7 months ago

Running on Zero

39

MOSS TTSD

📉

39

MOSS-TTSD: Text to Spoken Dialogue Generation

liked a model 7 months ago

OpenMOSS-Team/MOSS-TTSD-v0

Text-to-Speech • 2B • Updated Jun 20, 2025 • 24 • 27

published a Space 7 months ago

Running on Zero

39

MOSS TTSD

📉

39

MOSS-TTSD: Text to Spoken Dialogue Generation

upvoted a paper 7 months ago

ReasonGen-R1: CoT for Autoregressive Image generation models through SFT and RL

Paper • 2505.24875 • Published May 30, 2025 • 10

upvoted 3 papers 10 months ago

World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning

Paper • 2503.10480 • Published Mar 13, 2025 • 55

Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models

Paper • 2410.02416 • Published Oct 3, 2024 • 34

SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

Paper • 2502.14786 • Published Feb 20, 2025 • 157