NVIDIA releases the Nemotron 3 model family with hybrid Mamba-Transformer architecture, LatentMoE, NVFP4 training, MTP layers, and multi-environment RL post-training for reasoning and agentic tasks.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CL 3representative citing papers
Multilingual pooling for quality classifiers outperforms monolingual baselines in rank stability and accuracy for LLM pretraining data selection across high- and low-resource languages.
citing papers explorer
-
NVIDIA Nemotron 3: Efficient and Open Intelligence
NVIDIA releases the Nemotron 3 model family with hybrid Mamba-Transformer architecture, LatentMoE, NVFP4 training, MTP layers, and multi-environment RL post-training for reasoning and agentic tasks.
-
Toward Cross-Lingual Quality Classifiers for Multilingual Pretraining Data Selection
Multilingual pooling for quality classifiers outperforms monolingual baselines in rank stability and accuracy for LLM pretraining data selection across high- and low-resource languages.
- Compute Optimal Tokenization