Qwen

Enterprise

company

https://qwen.ai/

alibaba_qwen

QwenLM

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

loubnabnl authored a paper about 17 hours ago

SmolVLM: Redefining small and efficient multimodal models

bluelike updated a model 2 days ago

Qwen/Qwen2.5-VL-32B-Instruct-AWQ

bluelike updated a model 2 days ago

Qwen/Qwen2.5-VL-7B-Instruct-AWQ

View all activity

Qwen's activity

loubnabnl

authored a paper about 17 hours ago

SmolVLM: Redefining small and efficient multimodal models

Paper • 2504.05299 • Published 1 day ago • 94

AdinaY

posted an update about 17 hours ago

Post

911

IndexTTS 📢 a TTS built on XTTS + Tortoise, released by BiliBili - a Chinese video sharing platform/community.
Model: IndexTeam/Index-TTS
Demo: IndexTeam/IndexTTS

✨Chinese pronunciation correction via pinyin
✨Pause control via punctuation
✨Improved speaker conditioning & audio quality (BigVGAN2)
✨Trained on 10k+ hours

AdinaY

posted an update about 18 hours ago

Post

520

MAYE🎈a from-scratch RL framework for Vision Language Models, released by GAIR - an active research group from the Chinese community.

✨Minimal & transparent pipeline with standard tools
✨Standardized eval to track training & reflection
✨Open Code & Dataset

Code:
https://github.com/GAIR-NLP/MAYE?tab=readme-ov-file
Dataset:
ManTle/MAYE
Paper:
Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme (2504.02587)

bluelike

updated 6 models 2 days ago

hiyouga

in Qwen/Qwen2.5-Omni-7B 3 days ago

Open-source Fine-tuning script of Qwen2.5-Omni 7B 🚀

#29 opened 7 days ago by

hiyouga

littlebird13

in Qwen/Qwen2.5-Omni-7B 4 days ago

Japanese Text-to-Speech Not Working in Qwen2.5-Omni

#33 opened 5 days ago by

vigneshpalaniappan

Qwen2.5-Omni not working in the official website

#34 opened 4 days ago by

xcx0902

AdinaY

posted an update 5 days ago

Post

2665

SkyReels-A2 🚀 an open framework for controllable video generation from text + images, released by Skywork, KunLun

✨Model:
Skywork/SkyReels-A2
✨Paper:
SkyReels-A2: Compose Anything in Video Diffusion Transformers (2504.02436)

1 reply

AdinaY

posted an update 6 days ago

Post

1329

MegaTTS3 📢 an open TTS released by ByteDance

✨ 0.45B with Apache2.0
✨ Support English & Chinese
✨ High quality voice cloning
✨ Accent Intensity Control
ByteDance/MegaTTS3

AdinaY

posted an update 7 days ago

Post

2485

Dolphin 🐬 an open ASR model released by DataOceanAI, one of the biggest AI data provider in China 🔥

✨ Supports 40 Eastern languages & 22 Chinese dialects
✨ Apache2.0
✨ With 21.2M hours of data (7.4M open data)

Model:
DataoceanAI/dolphin-base
DataoceanAI/dolphin-small
Paper:
Dolphin: A Large-Scale Automatic Speech Recognition Model for Eastern Languages (2503.20212)

1 reply

AdinaY

posted an update 9 days ago

Post

1986

AutoGLM 沉思💫 FREE AI Agent released by ZhipuAI

✨ Think & Act simultaneously
✨ Based on a fully self-developed stack: GLM-4 for general, GLM-Z1 for inference, and GLM-Z1-Rumination for rumination
✨ Will openly share these models on April 14 🤯

Preview version👉 https://autoglm-research.zhipuai.cn/?channel=autoglm_android

AdinaY

posted an update 9 days ago

Post

1903

AReal-Boba 🔥 a fully open RL Frameworks released by AntGroup, an affiliate company of Alibaba.
inclusionAI/areal-boba-67e9f3fa5aeb74b76dcf5f0a
✨ 7B/32B - Apache2.0
✨ Outperform on math reasoning
✨ Replicating QwQ-32B with 200 data under $200
✨ All-in-one: weights, datasets, code & tech report