Fast and Stable Triangular Inversion for Delta-Rule Linear Transformers
Paper • 2605.21325 • Published • 1
Chieh Chang
hazdzz
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 8 days ago
Fast and Stable Triangular Inversion for Delta-Rule Linear Transformers upvoted a paper 8 days ago
Kalman Delta Networks: Uncertainty-aware Associative Memory upvoted a paper 8 days ago
Delta Attention ResidualsOrganizations
None yet
upvoted 14
papers 8 days ago
Kalman Delta Networks: Uncertainty-aware Associative Memory
Paper • 2609.07816 • Published • 31
Delta Attention Residuals
Paper • 2605.18855 • Published • 9
DeltaProduct: Improving State-Tracking in Linear RNNs via Householder Products
Paper • 2502.10297 • Published • 1
LUCID: Attention with Preconditioned Representations
Paper • 2602.10410 • Published • 2
Triadic Linear Attention: Three-Dimensional Recurrent States for Long-Context Sequence Modeling
Paper • 2609.36529 • Published • 39
Kimi Linear: An Expressive, Efficient Attention Architecture
Paper • 2510.26692 • Published • 139
Erase-then-Delta Attention: Decoupling Erase and Write Addresses in Delta-Rule Linear Attention
Paper • 2606.26560 • Published • 4
Complex KDA: Understanding and Enhancing the Expressivity of Kimi Delta Attention
Paper • 2609.24797 • Published • 13
Linear Attention Architectures: Mechanisms, Trade-offs, and Cross-Layer Routing
Paper • 2607.07953 • Published • 16
Gated Delta Networks: Improving Mamba2 with Delta Rule
Paper • 2412.06464 • Published • 19
Parallelizing Linear Transformers with the Delta Rule over Sequence Length
Paper • 2406.06484 • Published • 5
Preconditioned DeltaNet: Curvature-aware Sequence Modeling for Linear Recurrences
Paper • 2604.21100 • Published • 1
OSDN: Improving Delta Rule with Provable Online Preconditioning in Linear Attention
Paper • 2605.13473 • Published • 2
upvoted a paper 3 months ago