"au:"Zhijian Liu"" — arXiv2 SearchShowing 1–8 of 8 results
/ Date/ Name
Jun 19, 2025SparseLoRA: Accelerating LLM Fine-Tuning with Contextual SparsityMay 28, 2025Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel DecodingDec 5, 2024NVILA: Efficient Frontier Visual Language ModelsDec 19, 2023StreamDiffusion: A Pipeline-level Solution for Real-time Interactive GenerationApr 25, 2022Enable Deep Learning on Mobile Devices: Methods, Systems, and ApplicationsApr 21, 2022TorchSparse: Efficient Point Cloud Inference EngineMay 28, 2020HAT: Hardware-Aware Transformers for Efficient Natural Language ProcessingJun 21, 2019Deep Leakage from Gradients