collaborators

11 papers

cs.LG2026

SOAP, Muon, and Beyond: Pushing LLM Pretraining Scales

Mikail Khona, Aditya Vavre, Boxiang Wang +11

Higher-order optimizers such as Muon and SOAP offer faster convergence than AdamW, but their computational cost and numerical stability challenges have limited adoption at scale. I…

cs.CV2026

Elastic ViTs from Pretrained Models without Retraining

Walter Simoncini, Michael Dorkenwald, Tijmen Blankevoort +2

Vision foundation models achieve remarkable performance but are only available in a limited set of pre-determined sizes, forcing sub-optimal deployment choices under real-world con…

cs.LG2026

Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

NVIDIA, :, Aakshita Chandiramani +544

We describe the pre-training, post-training, and quantization of Nemotron 3 Super, a 120 billion (active 12 billion) parameter hybrid Mamba-Attention Mixture-of-Experts model. Nemo…

cs.LG2026

Quantization-Aware Distillation for NVFP4 Inference Accuracy Recovery

Meng Xin, Sweta Priyadarshi, Jingyu Xin +26

This technical report presents quantization-aware distillation (QAD) and our best practices for recovering accuracy of NVFP4-quantized large language models (LLMs) and vision-langu…

cs.CL2026

Data Repetition Beats Data Scaling in Long-CoT Supervised Fine-Tuning

Dawid J. Kopiczko, Sagar Vaze, Tijmen Blankevoort +1

Supervised fine-tuning (SFT) on chain-of-thought data is an essential post-training step for reasoning language models. Standard machine learning intuition suggests that training w…

cs.CL2025

NVIDIA Nemotron 3: Efficient and Open Intelligence

NVIDIA, :, Aaron Blakeman +356

We introduce the Nemotron 3 family of models - Nano, Super, and Ultra. These models deliver strong agentic, reasoning, and conversational capabilities. The Nemotron 3 family uses a…