
AItinerary (Preview)
Optimizing Compact Convolutional Transformers with FlashAttention and fused Triton MLP kernels, reducing memory without accuracy loss.
Ablation study of Neural Radiance Fields across hyperparameters, samplers, dataset size, and resolution, analyzing efficiency vs. quality.
Benchmarks of lensless camera reconstructions with GD/ADMM and learning-based methods on DiffuserCam, balancing speed and quality.
Let’s build something together.
See where visitors are coming from.