13 citations · 55 across the 19 of their papers we have counts for
20 papers
Uncertainty principles as forcing mechanisms
Laurent Massoulié
In this note we first consider the Heisenberg uncertainty principle. We show that it acts as a {\bf forcing mechanism} in the following sense. Real functions that approach its limi…
Error of randomized Milstein scheme for scalar SDEs with noisy information about coefficients and Wiener process
Paweł M. Morkisz, Paweł Przybyłowicz, Martyna Wiącek
We investigate the strong approximation of scalar stochastic differential equations when the available standard information about the drift coefficient, the diffusion coefficient,…
Cosmos 3: Omnimodal World Models for Physical AI
NVIDIA, :, Aditi +293
We introduce Cosmos 3, a family of omnimodal world models designed to jointly process and generate language, image, video, audio, and action sequences within a unified mixture-of-t…
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…
Hybrid Verified Decoding: Learning to Allocate Verification in Speculative Decoding
Xin Su, Dawid Majchrowski, Fangyuan Yu +5
Large Language Model (LLM) generation remains expensive because autoregressive decoding calls the model once for each new token. Speculative decoding reduces this cost by drafting…
NVIDIA Nemotron 3: Efficient and Open Intelligence
NVIDIA, :, Aaron Blakeman +356
We introduce the Nemotron 3 family of models - Nano, Super, and Ultra. These models deliver strong agentic, reasoning, and conversational capabilities. The Nemotron 3 family uses a…
Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
NVIDIA, :, Aaron Blakeman +311
We present Nemotron 3 Nano 30B-A3B, a Mixture-of-Experts hybrid Mamba-Transformer language model. Nemotron 3 Nano was pretrained on 25 trillion text tokens, including more than 3 t…
TSPP: A Unified Benchmarking Tool for Time-series Forecasting
Jan Bączek, Dmytro Zhylko, Gilberto Titericz +7
While machine learning has witnessed significant advancements, the emphasis has largely been on data acquisition and model creation. However, achieving a comprehensive assessment o…
Deep learning-based estimation of time-dependent parameters in Markov models with application to nonlinear regression and SDEs
Andrzej Kałuża, Paweł M. Morkisz, Bartłomiej Mulewicz +2
We present a novel deep learning method for estimating time-dependent parameters in Markov processes through discrete sampling. Departing from conventional machine learning, our ap…
On the randomized Euler algorithm under inexact information
Marcin Baranek, Andrzej Kałuża, Paweł M. Morkisz +2
This paper focuses on analyzing the error of the randomized Euler algorithm when only noisy information about the coefficients of the underlying stochastic differential equation (S…
A Framework for Large Scale Synthetic Graph Dataset Generation
Sajad Darabi, Piotr Bigaj, Dawid Majchrowski +3
Recently there has been increasing interest in developing and deploying deep graph learning algorithms for many tasks, such as fraud detection and recommender systems. Albeit, ther…
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…
Euler scheme for approximation of solution of nonlinear ODEs under inexact information
Natalia Czyżewska, Paweł M. Morkisz, Paweł Przybyłowicz
We investigate error of the Euler scheme in the case when the right-hand side function of the underlying ODE satisfies nonstandard assumptions such as local one-sided Lipschitz con…
Relative Molecule Self-Attention Transformer
Łukasz Maziarka, Dawid Majchrowski, Tomasz Danel +5
Self-supervised learning holds promise to revolutionize molecule property prediction - a central task to drug discovery and many more industries - by enabling data efficient learni…
Efficient GPU implementation of randomized SVD and its applications
Łukasz Struski, Paweł Morkisz, Przemysław Spurek +2
Matrix decompositions are ubiquitous in machine learning, including applications in dimensionality reduction, data compression and deep learning algorithms. Typical solutions for m…
Approximation of solutions of DDEs under nonstandard assumptions via Euler scheme
Natalia Czyżewska, Paweł M. Morkisz, Paweł Przybyłowicz
We deal with approximation of solutions of delay differential equations (DDEs) via the classical Euler algorithm. We investigate the pointwise error of the Euler scheme under nonst…
On mathematical aspects of evolution of dislocation density in metallic materials
Natalia Czyżewska, Jan Kusiak, Paweł Morkisz +5
This paper deals with the solution of delay differential equations describing evolution of dislocation density in metallic materials. Hardening, restoration, and recrystallization…
Randomized Runge-Kutta method -- stability and convergence under inexact information
Tomasz Bochacik, Maciej Goćwin, Paweł M. Morkisz +1
We deal with optimal approximation of solutions of ODEs under local Lipschitz condition and inexact discrete information about the right-hand side functions. We show that the rando…
Randomized derivative-free Milstein algorithm for efficient approximation of solutions of SDEs under noisy information
Paweł M. Morkisz, Paweł Przybyłowicz
We deal with pointwise approximation of solutions of scalar stochastic differential equations in the presence of informational noise about underlying drift and diffusion coefficien…
Optimal approximation of stochastic integrals in analytic noise model
Andrzej Kałuża, Paweł M. Morkisz, Paweł Przybyłowicz
We study approximate stochastic Itô integration of processes belonging to a class of progressively measurable stochastic processes that are Hölder continuous in the th mean. Ins…