-
GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting
Paper • 2403.08551 • Published • 8 -
4D Gaussian Splatting: Towards Efficient Novel View Synthesis for Dynamic Scenes
Paper • 2402.03307 • Published • 1 -
3DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videos
Paper • 2403.01444 • Published • 4 -
Boosting Neural Representations for Videos with a Conditional Decoder
Paper • 2402.18152 • Published
Collections
Discover the best community collections!
Collections including paper arxiv:2403.08551
-
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
Paper • 2402.17764 • Published • 605 -
MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases
Paper • 2402.14905 • Published • 127 -
YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information
Paper • 2402.13616 • Published • 46 -
Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers
Paper • 2402.19479 • Published • 32
-
SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling
Paper • 2312.15166 • Published • 56 -
PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU
Paper • 2312.12456 • Published • 40 -
Cached Transformers: Improving Transformers with Differentiable Memory Cache
Paper • 2312.12742 • Published • 12 -
Mini-GPTs: Efficient Large Language Models through Contextual Pruning
Paper • 2312.12682 • Published • 8