InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD
Paper
•
2404.06512
•
Published
•
30
Vision
-
-
Adapting LLaMA Decoder to Vision Transformer
Paper • 2404.06773 • Published • 18 -
Quantized Visual Geometry Grounded Transformer
Paper • 2509.21302 • Published • 8 -
Hyperspherical Latents Improve Continuous-Token Autoregressive Generation
Paper • 2509.24335 • Published • 8 -
VGGT-X: When VGGT Meets Dense Novel View Synthesis
Paper • 2509.25191 • Published • 18 -
LongLive: Real-time Interactive Long Video Generation
Paper • 2509.22622 • Published • 182 -
Self-Forcing++: Towards Minute-Scale High-Quality Video Generation
Paper • 2510.02283 • Published • 93