The models for the paper: Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts
Yingfa Chen
chen-yingfa
AI & ML interests
Long-context modeling, continual learning, architectures
Recent Activity
authored a paper 1 day ago
StateFlow: Sequence Pipeline Parallelism for Long-Context Modeling with Linear Recurrence authored a paper 1 day ago
Latent Compaction with Test-Time Training authored a paper 1 day ago
Frontier Language Models Struggle to Copy: Text Can Be Better Viewed in 2DOrganizations
None yet