3 papers
cs.LG2026
Shallow Encoding Emits Deep Memories
Mingyuan Ma, Yangmin Li, Harris Nover +4
Hybrid language models interleave a few softmax-attention layers with many linear-attention or state-space layers, so every layer keeps a memory of earlier tokens: a key-value cach…
math.CA2026
Uncertainty principles as forcing mechanisms
Laurent Massoulié
In this note we first consider the Heisenberg uncertainty principle. We show that it acts as a {\bf forcing mechanism} in the following sense. Real functions that approach its limi…
cs.CL2026
Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
NVIDIA, :, Aaron Blakeman +572
We introduce Nemotron 3 Ultra, a 550 billion total and 55 billion active parameter Mixture-of-Experts Hybrid Mamba-Attention language model. We pre-trained Nemotron 3 Ultra on 20 t…