52 citations · 112 across the 11 of their papers we have counts for
11 papers
Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
NVIDIA, :, Aaron Blakeman +572
We introduce Nemotron 3 Ultra, a 550 billion total and 55 billion active parameter Mixture-of-Experts Hybrid Mamba-Attention language model. We pre-trained Nemotron 3 Ultra on 20 t…
PersonaPlex: Voice and Role Control for Full Duplex Conversational Speech Models
Rajarshi Roy, Jonathan Raiman, Sang-gil Lee +5
Recent advances in duplex speech models have enabled natural, low-latency speech-to-speech interactions. However, existing models are restricted to a fixed role and voice, limiting…
CircuitVAE: Efficient and Scalable Latent Circuit Optimization
Jialin Song, Aidan Swope, Robert Kirby +4
Automatically designing fast and space-efficient digital circuits is challenging because circuits are discrete, must exactly implement the desired logic, and are costly to simulate…
ChipNeMo: Domain-Adapted LLMs for Chip Design
Mingjie Liu, Teodor-Dumitru Ene, Robert Kirby +39
ChipNeMo aims to explore the applications of large language models (LLMs) for industrial chip design. Instead of directly deploying off-the-shelf commercial or open-source LLMs, we…
Genetic Programming Based Symbolic Regression for Analytical Solutions to Differential Equations
Hongsup Oh, Roman Amici, Geoffrey Bomarito +3
In this paper, we present a machine learning method for the discovery of analytic solutions to differential equations. The method utilizes an inherently interpretable algorithm, ge…
PrefixRL: Optimization of Parallel Prefix Circuits using Deep Reinforcement Learning
Rajarshi Roy, Jonathan Raiman, Neel Kant +6
In this work, we present a reinforcement learning (RL) based approach to designing parallel prefix circuits such as adders or priority encoders that are fundamental to high-perform…
Meta-Learning with Adjoint Methods
Shibo Li, Zheng Wang, Akil Narayan +2
Model Agnostic Meta Learning (MAML) is widely used to find a good initialization for a family of tasks. Despite its success, a critical challenge in MAML is to calculate the gradie…
Guiding Global Placement With Reinforcement Learning
Robert Kirby, Kolby Nottingham, Rajarshi Roy +2
Recent advances in GPU accelerated global and detail placement have reduced the time to solution by an order of magnitude. This advancement allows us to leverage data driven optimi…
Physics Informed Deep Kernel Learning
Zheng Wang, Wei Xing, Robert Kirby +1
Deep kernel learning is a promising combination of deep neural networks and nonparametric function learning. However, as a data driven approach, the performance of deep kernel lear…
SDCNet: Video Prediction Using Spatially-Displaced Convolution
Fitsum A. Reda, Guilin Liu, Kevin J. Shih +5
We present an approach for high-resolution video frame prediction by conditioning on both past frames and past optical flows. Previous approaches rely on resampling past frames, gu…
Large Scale Language Modeling: Converging on 40GB of Text in Four Hours
Raul Puri, Robert Kirby, Nikolai Yakovenko +1
Recent work has shown how to train Convolutional Neural Networks (CNNs) rapidly on large image datasets, then transfer the knowledge gained from these models to a variety of tasks.…