2 papers
cs.CL2025
LoPT: Lossless Parallel Tokenization Acceleration for Long Context Inference of Large Language Model
Wei Shao, Lingchao Zheng, Pengyu Wang +3
Long context inference scenarios have become increasingly important for large language models, yet they introduce significant computational latency. While prior research has optimi…
cs.CV2025
3D Gaussian Splatting against Moving Objects for High-Fidelity Street Scene Reconstruction
Peizhen Zheng, Dongjing Jiang, Qingchong Jiao +2
The accurate reconstruction of dynamic street scenes is critical for applications in autonomous driving, augmented reality, and virtual reality. Traditional methods relying on dens…