Linear Attention Architectures: Mechanisms, Trade-offs, and Cross-Layer Routing Paper • 2607.07953 • Published 3 days ago • 5
Sparse Delta Memory: Scaling the State of Linear RNNs through Sparsity Paper • 2607.07386 • Published 3 days ago • 7
Nemotron-TwoTower: Diffusion Language Modeling with Pretrained Autoregressive Context Paper • 2606.26493 • Published 16 days ago • 3
Nemotron-Labs-TwoTower Collection Diffusion Language Modeling with Pretrained Autoregressive Nemotron 3 Models • 1 item • Updated 10 days ago • 6
Rethinking the Role of Efficient Attention in Hybrid Architectures Paper • 2606.15378 • Published 28 days ago • 19