6 31 135

QinyuanCheng

Cqy2019

AI & ML interests

None yet

Recent Activity

upvoted a paper about 15 hours ago

TL-GRPO: Turn-Level RL for Reasoning-Guided Iterative Optimization

liked a Space 5 days ago

chenxie95/Habibi-TTS

upvoted a paper 7 days ago

ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development

View all activity

Organizations

upvoted a paper about 15 hours ago

TL-GRPO: Turn-Level RL for Reasoning-Guided Iterative Optimization

Paper • 2601.16480 • Published 4 days ago • 49

liked a Space 5 days ago

Habibi TTS

🗣

F5-TTS Online Demo for Dev Test

upvoted a paper 7 days ago

ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development

Paper • 2601.11077 • Published 11 days ago • 63

reacted to AdinaY's post with 🔥 10 days ago

Post

702

More lightweight multimodal models are coming 👀

StepFun has been focused on multimodal AI from the very beginning. Their latest release a new foundational model: STEP3-VL🔥
https://huggingface.co/collections/stepfun-ai/step3-vl-10b
✨ 10B - Apache2.0
✨ Leads in the 10B class and competes with models 10–20× larger

liked 2 datasets 14 days ago

laion/aesthetics_v2_4.5

Viewer • Updated Sep 1, 2024 • 1.33B • 66 • 29

yfish/WESR-Bench

Viewer • Updated 18 days ago • 927 • 124 • 7

liked a dataset 15 days ago

Yejy53/Nano-consistent-150k

Updated Sep 17, 2025 • 157 • 41

reacted to AdinaY's post with 🔥 18 days ago

Post

635

MOSS Transcribe Diarize 🔊 A multimodal model for Speaker-Attributed, Time-Stamped Transcription from OpenMOSS.

MOSS Transcribe Diarize: Accurate Transcription with Speaker Diarization (2601.01554)
OpenMOSS-Team/MOSS-transcribe-diarize

✨ Single-pass end-to-end SATS
✨ 128k context, ~90 min audio
✨ Robust to overlap & noise