5 papers · 1 filter
HLA: Expressive Hybrid Linear Attention via Chunk-Wise Dynamic Mixing
Zhuokun Chen, Xi Lin, Xiyu Wu +3
Linear attention enables efficient long-context autoregressive decoding by compressing history into recurrent states, but this compression can make selective access to sparse and d…
HLA-WM: Hybrid Linear Attention for Long-Horizon Video World Models
Zhuokun Chen, Feng Chen, Xi Lin +4
Long-horizon video world models require persistent memory to preserve scene consistency over extended rollouts. Softmax attention retains the full generation history through a grow…
RDVSv2: A Large-scale Benchmark for RGB-D Video Salient Object Detection
Tianyu Li, Jiahao He, Keren Fu +1
We introduce RDVSv2, a large-scale benchmark for RGB-D video salient object detection (RGB-D VSOD) with dense frame-level annotations. Existing datasets in this emerging field are…
GrainGS: Gradient-Decoupled Gaussian Splatting for Efficient Dynamic Novel View Synthesis
Jiahao He, Yihua Shao, Zhengkai Zhao +6
Dynamic scene reconstruction with 3D Gaussian Splatting requires a balance between fine-grained motion modeling, structural stability, and compact representation. Existing per-prim…
Samba+: General and Accurate Salient Object Detection via A More Unified Mamba-based Framework
Wenzhuo Zhao, Keren Fu, Jiahao He +3
Existing salient object detection (SOD) models are generally constrained by the limited receptive fields of convolutional neural networks (CNNs) and quadratic computational complex…