الباحثون

Xiyu Wu

المنشورات 2

نسخة أولية وصول مفتوح

HLA: Expressive Hybrid Linear Attention via Chunk-Wise Dynamic Mixing

Zhuokun Chen, Xi Lin, Xiyu Wu وآخرون · 2026

Linear attention enables efficient long-context autoregressive decoding by compressing history into recurrent states, but this compression can make selective access to sparse and distant information difficult. Existing chunk-based extensions increase memory capacity, yet learned chunk-mixing coefficients may remain fix …

نسخة أولية وصول مفتوح

HLA-WM: Hybrid Linear Attention for Long-Horizon Video World Models

Zhuokun Chen, Feng Chen, Xi Lin وآخرون · 2026

Long-horizon video world models require persistent memory to preserve scene consistency over extended rollouts. Softmax attention retains the full generation history through a growing KV cache, whereas recurrent linear attention compresses history into fixed-size states with substantially lower memory cost. However, we …

المؤلفون المشاركون

Zhuokun Chen Feng Chen Xi Lin Jiahao He Jianfei Cai Bohan Zhuang