4 papers · 1 filter
VVS: Accelerating Speculative Decoding for Visual Autoregressive Generation via Partial Verification Skipping
Haotian Dong, Ye Li, Rongwei Lu +3
Visual autoregressive (AR) generation models have demonstrated strong potential for image generation, yet their next-token-prediction paradigm introduces considerable inference lat…
Accelerating Parallel Diffusion Model Serving with Residual Compression
Jiajun Luo, Yicheng Xiao, Jianru Xu +5
Diffusion models produce realistic images and videos but require substantial computational resources, necessitating multi-accelerator parallelism for real-time deployment. However,…
MesonGS: Post-training Compression of 3D Gaussians via Efficient Attribute Transformation
Shuzhao Xie, Weixiang Zhang, Chen Tang +4
3D Gaussian Splatting demonstrates excellent quality and speed in novel view synthesis. Nevertheless, the huge file size of the 3D Gaussians presents challenges for transmission an…
Retraining-free Model Quantization via One-Shot Weight-Coupling Learning
Chen Tang, Yuan Meng, Jiacheng Jiang +5
Quantization is of significance for compressing the over-parameterized deep neural models and deploying them on resource-limited devices. Fixed-precision quantization suffers from…