An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection Paper • 1904.09730 • Published Apr 22, 2019
EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens Paper • 2211.10636 • Published Nov 19, 2022
HiP Attention: Sparse Sub-Quadratic Attention with Hierarchical Attention Pruning Paper • 2406.09827 • Published Jun 14, 2024 • 2
VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video Understanding Paper • 2412.02186 • Published Dec 3, 2024 • 22
HoliSafe: Holistic Safety Benchmarking and Modeling with Safety Meta Token for Vision-Language Model Paper • 2506.04704 • Published Jun 5 • 1
KOALA: Self-Attention Matters in Knowledge Distillation of Latent Diffusion Models for Memory-Efficient and Fast Image Synthesis Paper • 2312.04005 • Published Dec 7, 2023 • 2