Picture for Xiaohuan Pei

Xiaohuan Pei

Cross-Self KV Cache Pruning for Efficient Vision-Language Inference

Add code
Dec 05, 2024
Viaarxiv icon

EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba

Add code
Mar 15, 2024
Viaarxiv icon

LocalMamba: Visual State Space Model with Windowed Selective Scan

Add code
Mar 14, 2024
Viaarxiv icon

Neural Architecture Retrieval

Add code
Jul 16, 2023
Viaarxiv icon

GPT Self-Supervision for a Better Data Annotator

Add code
Jun 08, 2023
Viaarxiv icon