7 citations · 23 across the 8 of their papers we have counts for
8 papers
Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models
NVIDIA, :, Aaron Blakeman +198
As inference-time scaling becomes critical for enhanced reasoning capabilities, it is increasingly becoming important to build models that are efficient to infer. We introduce Nemo…
Tiered Pruning for Efficient Differentialble Inference-Aware Neural Architecture Search
Sławomir Kierat, Mateusz Sieniawski, Denys Fridman +4
We propose three novel pruning techniques to improve the cost and results of inference-aware Differentiable Neural Architecture Search (DNAS). First, we introduce Prunode, a stocha…
GPUNet: Searching the Deployable Convolution Neural Networks for GPUs
Linnan Wang, Chenhan Yu, Satish Salian +3
Customizing Convolution Neural Networks (CNN) for production use has been a challenging task for DL practitioners. This paper intends to expedite the model customization with a mod…
Pay Attention when Required
Swetha Mandava, Szymon Migacz, Alex Fit Florea
Transformer-based models consist of interleaved feed-forward blocks - that capture content meaning, and relatively more expensive self-attention blocks - that capture context meani…
Optimizing Multi-GPU Parallelization Strategies for Deep Learning Training
Saptadeep Pal, Eiman Ebrahimi, Arslan Zulfiqar +5
Deploying deep learning (DL) models across multiple compute devices to train large and complex models continues to grow in importance because of the demand for faster and more freq…
Charges of the gravitational field and (3+1) decomposition of CYK tensors part 2
Jacek Jezierski, Szymon Migacz
The work describes the method of construction of charges (conserved quantities) for the gravity field in the (3 + 1) decomposition. The presented construction uses tensors of the e…
MDFS - MultiDimensional Feature Selection
Radosław Piliszek, Krzysztof Mnich, Szymon Migacz +4
Identification of informative variables in an information system is often performed using simple one-dimensional filtering procedures that discard information about interactions be…
The 3+1 decomposition of Conformal Yano-Killing tensors and "momentary" charges for spin-2 field
Jacek Jezierski, Szymon Migacz
The "fully charged" spin-2 field solution is presented. This is an analog of the Coulomb solution in electrodynamics and represents the "non-waving" part of the spin-2 field theory…