Mamba-3: Improved Sequence Modeling using State Space Principles Paper • 2603.15569 • Published Mar 16 • 6
FlashAttention-4: Algorithm and Kernel Pipelining Co-Design for Asymmetric Hardware Scaling Paper • 2603.05451 • Published Mar 5 • 1
M1: Towards Scalable Test-Time Compute with Mamba Reasoning Models Paper • 2504.10449 • Published Apr 14, 2025 • 15