Search papers, labs, and topics across Lattice.
2
0
3
Achieving near-FP16 accuracy with 4-bit quantization, TwinQuant offers a groundbreaking approach to optimizing large language model inference speed and efficiency.
Achieve high-fidelity CBCT reconstructions from ultra sparse-view data by decoupling geometry and texture in 3D Gaussian Splatting, enabling physically consistent residual detail compensation.
