ByteDance/Sa2VA-Qwen3-VL-4B-SAM3
Image-Text-to-Text • 5B • Updated • 102 • 1
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
When Teachers Mislead: Spurious-Signal-Aware On-Policy Distillation
SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks
ByteDance/Sa2VA-LLaVA-1.5-7B
Image-Text-to-Text • 7B • Updated • 22
ByteDance/UniVR-34B-Planning
Image-Text-to-Text • Updated • 15 • 12
ByteDance/Bernini-Diffusers
Image-Text-to-Video • Updated • 38
ByteDance/EvoQuality
Image-Text-to-Text • 8B • Updated • 245 • 30
ByteDance/Bernini-R-1.3B-Diffusers
Image-Text-to-Video • 1B • Updated • 24
ByteDance/Ouro-1.4B-Thinking
Text Generation • 1B • Updated • 8.95k • 46
ByteDance/Bernini-R-Diffusers
Image-Text-to-Video • 14B • Updated • 18
ByteDance/Bernini-R
Image-Text-to-Video • Updated • 152 • 296
ByteDance/Ouro-2.6B-Thinking
Text Generation • 3B • Updated • 5.97k • 142
ByteDance/Q-Insight
Updated • 24
ByteDance/Ouro-2.6B
Text Generation • 3B • Updated • 4.98k • 90
ByteDance/Ouro-1.4B
Text Generation • 1B • Updated • 33.3k • 109
ByteDance/Dolphin-v2
Image-Text-to-Text • 4B • Updated • 547 • 114
ByteDance/BindWeave
Image-to-Video • Updated • 1.07k • 91
ByteDance/Sa2VA-Qwen3-VL-2B
Image-Text-to-Text • 3B • Updated • 70 • 16
ByteDance/Dolphin-1.5
Image-Text-to-Text • 0.4B • Updated • 534 • 39
ByteDance/FaceCLIP
Text-to-Image • Updated • 92
ByteDance/Video-As-Prompt-CogVideoX-5B
Image-to-Video • 11B • Updated • 41 • 25
ByteDance/Video-As-Prompt-Wan2.1-14B
Image-to-Video • 21B • Updated • 42 • 49
ByteDance/Sa2VA-Qwen3-VL-4B
Image-Text-to-Text • 5B • Updated • 895 • 18
ByteDance/Sa2VA-InternVL3-14B
Image-Text-to-Text • 15B • Updated • 25 • 10
ByteDance/Sa2VA-Qwen2_5-VL-7B
Image-Text-to-Text • 9B • Updated • 99 • 5
ByteDance/Sa2VA-InternVL3-8B
Image-Text-to-Text • 8B • Updated • 170 • 6
ByteDance/Sa2VA-Qwen2_5-VL-3B
Image-Text-to-Text • 4B • Updated • 77 • 3
ByteDance/Sa2VA-InternVL3-2B
Image-Text-to-Text • 2B • Updated • 55 • 2
ByteDance/lynx
Image-to-Video • Updated • • 141
ByteDance/Sa2VA-26B
Image-Text-to-Text • 26B • Updated • 145 • 32
ByteDance/Sa2VA-8B
Image-Text-to-Text • 8B • Updated • 525 • 64
ByteDance/Sa2VA-1B
Image-Text-to-Text • 1B • Updated • 517 • 31