YOSE: Selecting Only Essential Tokens for Faster Video Object Removal
Researchers propose YOSE, a method that significantly improves the efficiency of Diffusion Transformer-based video objec…
🏷️ Inference Acceleration
4 articles about 'Inference Acceleration'
NVIDIA TensorRT Accelerates Neural Network Inference in Unreal Engine NNE
NVIDIA has released the TensorRT for RTX runtime plugin for Unreal Engine's NNE, dramatically boosting neural network in…
SpecTr-GBV: Multi-Draft Block Verification Accelerates Speculative Decoding
A new study proposes SpecTr-GBV, the first method to combine multi-draft strategies with block verification techniques, …
Accelerating Frequency-Domain Diffusion Model Inference: A Deep Dive into the E²-CRF Caching Strategy
A latest arXiv paper proposes the E²-CRF method, leveraging two key structural properties — spectral localization and mi…
1