832 citations · 1.9k across the 80 of their papers we have counts for
17 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…
LatentMoE: Toward Optimal Accuracy per FLOP and Parameter in Mixture of Experts
Venmugil Elango, Nidhi Bhatia, Roger Waleffe +13
Mixture of Experts (MoEs) have become a central component of many state-of-the-art open-source and proprietary large language models. Despite their widespread adoption, it remains…
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…
MoE Parallel Folding: Heterogeneous Parallelism Mappings for Efficient Large-Scale MoE Model Training with Megatron Core
Dennis Liu, Zijie Yan, Xin Yao +15
Mixture of Experts (MoE) models enhance neural network scalability by dynamically selecting relevant experts per input token, enabling larger model sizes while maintaining manageab…
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…
FP8 Formats for Deep Learning
Paulius Micikevicius, Dusan Stosic, Neil Burgess +12
FP8 is a natural progression for accelerating deep learning training inference beyond the 16-bit formats common in modern processors. In this paper we propose an 8-bit floating poi…
Reducing Activation Recomputation in Large Transformer Models
Vijay Korthikanti, Jared Casper, Sangkug Lym +4
Training large transformer models is one of the most important computational challenges of modern AI. In this paper, we show how to significantly accelerate training of large trans…
Trace norm regularization and faster inference for embedded speech recognition RNNs
Markus Kliegl, Siddharth Goyal, Kexin Zhao +2
We propose and evaluate new techniques for compressing and speeding up dense matrix multiplications as found in the fully connected and recurrent layers of neural networks for embe…