Ruisi Cai

9

Papers

13

Total Citations

Papers (9)

Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing

LLaMaFlex: Many-in-one LLMs via Generalized Pruning and Weight Sharing

FlexGS: Train Once, Deploy Everywhere with Many-in-One Flexible 3D Gaussian Splatting

Robust Mixture-of-Expert Training for Convolutional Neural Networks

Steepest Descent Density Control for Compact 3D Gaussian Splatting

LoCoCo: Dropping In Convolutions for Long Context Compression

Flextron: Many-in-One Flexible Large Language Model

Randomized Channel Shuffling: Minimal-Overhead Backdoor Attack Detection without Clean Datasets

H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models