Wang Chengyao's picture

Wang Chengyao

wcy1122

·

https://wcy1122.github.io/

AI & ML interests

Multimodal Intelligence

Recent Activity

upvoted a paper 2 days ago

OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence

liked a model 22 days ago

moonshotai/Kimi-K2.5

upvoted a paper about 2 months ago

mHC: Manifold-Constrained Hyper-Connections

View all activity

Organizations

wcy1122 's models 10

wcy1122/Qwen2.5-VL-3B-ViT

0.7B • Updated Oct 11, 2025 • 1

wcy1122/MGM-Omni-TTS-2B-0927

Any-to-Any • 2B • Updated Oct 7, 2025 • 64 • 10

wcy1122/MGM-Omni-7B

Text Generation • 8B • Updated Oct 7, 2025 • 69 • 5

wcy1122/MGM-Omni-32B

Text Generation • 33B • Updated Aug 17, 2025 • 2 • 5

wcy1122/MGM-Omni-TTS-2B

Text-to-Speech • 2B • Updated Aug 17, 2025 • 3

wcy1122/MGM-Omni-TTS-4B

Text-to-Speech • 5B • Updated Aug 17, 2025 • 2 • 5

wcy1122/MGM-Omni-TTS-0.6B

Text-to-Speech • 0.7B • Updated Aug 17, 2025 • 1 • 4

wcy1122/Qwen2.5-VL-32B-ViT

0.7B • Updated Aug 15, 2025 • 1

wcy1122/Qwen2A-7B-Encoder

0.6B • Updated Aug 8, 2025 • 86 • 1

wcy1122/Qwen2.5-VL-7B-ViT

0.7B • Updated Aug 8, 2025 • 83 • 1