ARL2 replaces quadratic cross-frame attention in AR video diffusion with a fixed-size recurrent state, achieving linear-time scaling and constant memory while preserving quality.
ArXiv , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
TempCompass benchmark reveals that state-of-the-art Video LLMs have poor ability to perceive temporal aspects such as speed, direction, and ordering in videos.
A graph-spectral importance score based on layer-wise structural distortion between pre- and post-activation neuron graphs identifies removable neurons for iterative pruning without intermediate updates, followed by recovery fine-tuning.
citing papers explorer
-
Attend Locally, Remember Linearly: Linear Attention as Cross-Frame Memory for Autoregressive Video Diffusion
ARL2 replaces quadratic cross-frame attention in AR video diffusion with a fixed-size recurrent state, achieving linear-time scaling and constant memory while preserving quality.
-
TempCompass: Do Video LLMs Really Understand Videos?
TempCompass benchmark reveals that state-of-the-art Video LLMs have poor ability to perceive temporal aspects such as speed, direction, and ordering in videos.
-
Spectral structural distortion reveals redundant neurons in neural networks
A graph-spectral importance score based on layer-wise structural distortion between pre- and post-activation neuron graphs identifies removable neurons for iterative pruning without intermediate updates, followed by recovery fine-tuning.