28 citations · 90 across the 65 of their papers we have counts for
13 papers · 1 filter
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…
Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence
NVIDIA, :, Amala Sanjay Deshmukh +204
We introduce Nemotron 3 Nano Omni, the latest model in the Nemotron multimodal series and the first to natively support audio inputs alongside text, images, and video. Nemotron 3 N…
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…
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…
NVIDIA Nemotron Nano V2 VL
NVIDIA, :, Amala Sanjay Deshmukh +121
We introduce Nemotron Nano V2 VL, the latest model of the Nemotron vision-language series designed for strong real-world document understanding, long video comprehension, and reaso…
RLP: Reinforcement as a Pretraining Objective
Ali Hatamizadeh, Syeda Nahida Akter, Shrimai Prabhumoye +5
The dominant paradigm for training large reasoning models starts with pre-training using next-token prediction loss on vast amounts of data. Reinforcement learning, while powerful…
Front-Loading Reasoning: The Synergy between Pretraining and Post-Training Data
Syeda Nahida Akter, Shrimai Prabhumoye, Eric Nyberg +4
The prevailing paradigm for enhancing the reasoning abilities of LLMs revolves around post-training on high-quality, reasoning-intensive data. While emerging literature suggests th…
FusionFactory: Fusing LLM Capabilities with Multi-LLM Log Data
Tao Feng, Haozhen Zhang, Zijie Lei +5
The rapid advancement of large language models (LLMs) has created a diverse landscape of models, each excelling at different tasks. This diversity drives researchers to employ mult…
AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning
Yang Chen, Zhuolin Yang, Zihan Liu +5
Despite recent progress in large-scale reinforcement learning (RL) for reasoning, the training recipe for building high-performing reasoning models remains elusive. Key implementat…
Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning
Jaehun Jung, Seungju Han, Ximing Lu +7
Effective generalization in language models depends critically on the diversity of their training data. Yet existing diversity metrics often fall short of this goal, relying on sur…
Nemotron-CrossThink: Scaling Self-Learning beyond Math Reasoning
Syeda Nahida Akter, Shrimai Prabhumoye, Matvei Novikov +8
Large Language Models (LLMs) have shown strong reasoning capabilities, particularly when enhanced through Reinforcement Learning (RL). While prior work has successfully applied RL…
An Empirical Study of Mamba-based Language Models
Roger Waleffe, Wonmin Byeon, Duncan Riach +13
Selective state-space models (SSMs) like Mamba overcome some of the shortcomings of Transformers, such as quadratic computational complexity with sequence length and large inferenc…
ODIN: Disentangled Reward Mitigates Hacking in RLHF
Lichang Chen, Chen Zhu, Davit Soselia +6
In this work, we study the issue of reward hacking on the response length, a challenge emerging in Reinforcement Learning from Human Feedback (RLHF) on LLMs. A well-formatted, verb…