TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models
Paper
• 2512.02014 • Published
• 73
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
OpenVision 3: A Family of Unified Visual Encoder for Both Understanding and Generation
MedVLSynther: Synthesizing High-Quality Visual Question Answering from Medical Documents with Generator-Verifier LMMs
xk-huangÂ
authored 4 papers 5 days ago
Scaling Zero-Shot Reference-to-Video Generation
Paper
• 2512.06905 • Published
• 29
OneStory: Coherent Multi-Shot Video Generation with Adaptive Memory
Paper
• 2512.07802 • Published
• 46
VecGlypher: Unified Vector Glyph Generation with Language Models
Paper
• 2602.21461 • Published
• 11
xk-huangÂ
submitted a paper to Daily Papers 6 days ago
Letian2003Â
updated a collection about 1 month ago
cihangxieÂ
updated a collection about 1 month ago
cihangxieÂ
submitted a paper to Daily Papers about 1 month ago
Letian2003Â
updated a collection about 1 month ago
Letian2003Â
updated a model about 1 month ago
Letian2003Â
published a model about 1 month ago
xk-huangÂ
authored 2 papers 3 months ago
xk-huangÂ
updated a collection 4 months ago
XianhangÂ
authored 5 papers 5 months ago
Unleashing the Power of Visual Prompting At the Pixel Level
Paper
• 2212.10556 • Published
CLIPS: An Enhanced CLIP Framework for Learning with Synthetic Captions
Paper
• 2411.16828 • Published
• 1
OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning
Paper
• 2505.04601 • Published
• 29
Autoregressive Pretraining with Mamba in Vision
Paper
• 2406.07537 • Published
OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning
Paper
• 2509.01644 • Published
• 34