2 papers
cs.CV2024
FlexAttention for Efficient High-Resolution Vision-Language Models
Junyan Li, Delin Chen, Tianle Cai +5
Current high-resolution vision-language models encode images as high-resolution image tokens and exhaustively take all these tokens to compute attention, which significantly increa…
cs.CL2024
JetMoE: Reaching Llama2 Performance with 0.1M Dollars
Yikang Shen, Zhen Guo, Tianle Cai +1
Large Language Models (LLMs) have achieved remarkable results, but their increasing resource demand has become a major obstacle to the development of powerful and accessible super-…