Jiahui Hu

Turing-20B-A2B achieves exceptional long-context capabilities with only a fraction of its parameters activated, pushing the boundaries of efficiency in physical AI applications.

Achieving 5-7x speedup in diffusion models without sacrificing quality, LinCa redefines the efficiency of feature caching through adaptive prediction strategies.

Privacy-sensitive visual and textual information can be recovered from deep-layer LVLM hidden states, exposing significant risks in collaborative inference.

Achieving competitive performance in Vision-Language Models while reducing computational overhead could revolutionize their deployment on edge devices.

TuringViT outperforms leading ViT models with just 10% of the training data, making state-of-the-art vision technology accessible to a wider audience.