Haotian Tang

6

Papers

0

Total Citations

Papers (6)

NVILA: Efficient Frontier Visual Language Models

MoST: Multi-Modality Scene Tokenization for Motion Prediction

FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer

SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer

Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution

Point-Voxel CNN for Efficient 3D Deep Learning