48 citations · 72 across the 13 of their papers we have counts for
14 papers
NVIDIA-labs OO Agents: Native Python Object-Oriented Agents
Paul Furgale, Severin Klingler, James Nolan +12
Traditional agent development is split across prompt templates, tool schemas, callback code, and workflow graphs. We present NVIDIA Object-Oriented Agents (NOOA), a model-agnostic…
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…
Workspace Optimization: How to Train Your Agent
Elad Sarafian, Gal Kaplun, Ron Banner +2
Modern agents built on frontier language models often cannot adapt their weights. What, then, remains trainable? We argue it is the agent's \emph{workspace}, the structured externa…
Corgi^2: A Hybrid Offline-Online Approach To Storage-Aware Data Shuffling For SGD
Etay Livne, Gal Kaplun, Eran Malach +1
When using Stochastic Gradient Descent (SGD) for training machine learning models, it is often crucial to provide the model with examples sampled at random from the dataset. Howeve…
Beyond Implicit Bias: The Insignificance of SGD Noise in Online Learning
Nikhil Vyas, Depen Morwani, Rosie Zhao +3
The success of SGD in deep learning has been ascribed by prior works to the implicit bias induced by finite batch sizes ("SGD noise"). While prior works focused on offline learning…
Less is More: Selective Layer Finetuning with SubTuning
Gal Kaplun, Andrey Gurevich, Tal Swisa +3
Finetuning a pretrained model has become a standard approach for training neural networks on novel tasks, resulting in fast convergence and improved performance. In this work, we s…
Knowledge Distillation: Bad Models Can Be Good Role Models
Gal Kaplun, Eran Malach, Preetum Nakkiran +1
Large neural networks trained in the overparameterized regime are able to fit noise to zero train error. Recent work \citep{nakkiran2020distributional} has empirically observed tha…
Deconstructing Distributions: A Pointwise Framework of Learning
Gal Kaplun, Nikhil Ghosh, Saurabh Garg +2
In machine learning, we traditionally evaluate the performance of a single model, averaged over a collection of test inputs. In this work, we propose a new approach: we measure the…
For Manifold Learning, Deep Neural Networks can be Locality Sensitive Hash Functions
Nishanth Dikkala, Gal Kaplun, Rina Panigrahy
It is well established that training deep neural networks gives useful representations that capture essential features of the inputs. However, these representations are poorly unde…
For self-supervised learning, Rationality implies generalization, provably
Yamini Bansal, Gal Kaplun, Boaz Barak
We prove a new upper bound on the generalization gap of classifiers that are obtained by first using self-supervision to learn a representation of the training data, and then f…
Robustness from Simple Classifiers
Sharon Qian, Dimitris Kalimeris, Gal Kaplun +1
Despite the vast success of Deep Neural Networks in numerous application domains, it has been shown that such models are not robust i.e., they are vulnerable to small adversarial p…
Deep Double Descent: Where Bigger Models and More Data Hurt
Preetum Nakkiran, Gal Kaplun, Yamini Bansal +3
We show that a variety of modern deep learning tasks exhibit a "double-descent" phenomenon where, as we increase model size, performance first gets worse and then gets better. More…
SGD on Neural Networks Learns Functions of Increasing Complexity
Preetum Nakkiran, Gal Kaplun, Dimitris Kalimeris +4
We perform an experimental study of the dynamics of Stochastic Gradient Descent (SGD) in learning deep neural networks for several real and synthetic classification tasks. We show…
Robust Influence Maximization for Hyperparametric Models
Dimitris Kalimeris, Gal Kaplun, Yaron Singer
In this paper, we study the problem of robust influence maximization in the independent cascade model under a hyperparametric assumption. In social networks users influence and are…