tencent/HY-Embodied-0.5
Image-Text-to-Text • 4B • Updated • 136 • 14
AI & ML interests
None defined yet.
Recent Activity
Papers
UI-Voyager: A Self-Evolving GUI Agent Learning via Failed Experience
OmniWeaving: Towards Unified Video Generation with Free-form Composition and Reasoning
tencent/HY-OmniWeaving
Updated • 238
tencent/Sequential-Hidden-Decoding-8B-n8-Instruct
Text Generation • 13B • Updated • 22 • 6
tencent/VersaViT
Updated • 25 • 5
tencent/HY-MT1.5-7B
Translation • 8B • Updated • 6.74k • 147
tencent/Covo-Audio-Chat
Audio-to-Audio • 8B • Updated • 691 • 79
tencent/Sequential-Hidden-Decoding-8B-n8
13B • Updated • 23 • 13
tencent/Penguin-VL-2B
Text Generation • 2B • Updated • 3.36k • 36
tencent/Penguin-VL-8B
Text Generation • 9B • Updated • 7.51k • 74
tencent/POINTS-GUI-G
Image-Text-to-Text • 9B • Updated • 340 • 18
tencent/Sequential-Hidden-Decoding-8B-n2
9B • Updated • 14 • 9
tencent/Sequential-Hidden-Decoding-8B-n4
10B • Updated • 11 • 10
tencent/Penguin-Encoder
Feature Extraction • 0.4B • Updated • 7.72k • 21
tencent/HY-WorldPlay
Image-to-Video • Updated • 1.11k • 330
tencent/HY-WU
Image-Text-to-Image • 8B • Updated • 630 • 27
tencent/SongGeneration
Text-to-Audio • Updated • 1.57k • 327
tencent/StableToken
Updated • 7
tencent/Youtu-LLM-2B
Text Generation • 2B • Updated • 879 • 227
tencent/Youtu-LLM-2B-Base
Text Generation • Updated • 3.46k • 42
tencent/Youtu-VL-4B-Instruct-GGUF
Image-Text-to-Text • 5B • Updated • 696 • 61
tencent/Youtu-VL-4B-Instruct
Image-Text-to-Text • 5B • Updated • 422 • 154
tencent/KaLM-Embedding-Gemma3-12B-2511
Sentence Similarity • Updated • 93.6k • 88
tencent/HY3D-Bench
Image-to-3D • Updated • 24 • 43
tencent/Youtu-HiChunk
Feature Extraction • Updated • 11 • 15
tencent/HunyuanImage-3.0-Instruct-Distil
Image-to-Image • 83B • Updated • 595 • 55
tencent/HunyuanImage-3.0-Instruct
Image-to-Image • 83B • Updated • 2.63k • • 396
tencent/Youtu-Parsing
Image-Text-to-Text • 3B • Updated • 274 • 39
tencent/HunyuanImage-3.0
Text-to-Image • Updated • 98.1k • • 661
tencent/HY-Video-PRFL
Updated • 18
tencent/HunyuanOCR
Image-Text-to-Text • Updated • 165k • 563