Ping Luo (羅平)
Ping Luo (羅平)
Home
News&Talks
Publications
Members
Projects
Contact
Light
Dark
Automatic
Foundation Model is Efficient Multimodal Multitask Model Selector
Wenqi Shao
,
Chonghe Jiang
,
Kaipeng Zhang
,
Yu Qiao
,
Ping Luo
September 2023
PDF
Type
Conference paper
Publication
Thirty-seventh Annual Conference on Neural Information Processing Systems
(
NeurIPS
) 2023
Related
OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
Embodiedgpt: Vision-language pre-training via embodied chain of thought
Visionllm: Large language model is also an open-ended decoder for vision-centric tasks
Dynamic Token Normalization improves Vision Transformers
Rethinking the Pruning Criteria for Convolutional Neural Network
Cite
×
