Related papers: NeMo: a toolkit for building AI applications using…
Application domains that require considering relationships among objects which have real-valued attributes are becoming even more important. In this paper we propose NeuralLog, a first-order logic language that is compiled to a neural…
In this paper, we introduce a benchmarking framework within the open-source NVIDIA PhysicsNeMo-CFD framework designed to systematically assess the accuracy, performance, scalability, and generalization capabilities of AI models for…
Memristors have shown promising features for enhancing neuromorphic computing concepts and AI hardware accelerators. In this paper, we present a user-friendly software infrastructure that allows emulating a wide range of neuromorphic…
Image classification methods are usually trained to perform predictions taking into account a predefined group of known classes. Real-world problems, however, may not allow for a full knowledge of the input and label spaces, making failures…
This paper presents NEUROSPF, a tool for the symbolic analysis of neural networks. Given a trained neural network model, the tool extracts the architecture and model parameters and translates them into a Java representation that is amenable…
This study presents an NNTile framework for training large deep neural networks in heterogeneous clusters. The NNTile is based on a StarPU library, which implements task-based parallelism and schedules all provided tasks onto all available…
The rise of social media platforms has brought about a new digital culture called memes. Memes, which combine visuals and text, can strongly influence public opinions on social and cultural issues. As a result, people have become interested…
Material node graphs are programs that generate the 2D channels of procedural materials, including geometry such as roughness and displacement maps, and reflectance such as albedo and conductivity maps. They are essential in computer…
Continuous embeddings of tokens in computer programs have been used to support a variety of software development tools, including readability, code search, and program repair. Contextual embeddings are common in natural language processing…
Existing 3D human motion generation and understanding methods often exhibit limited interpretability, restricting effective mutual enhancement between these inherently related tasks. While current unified frameworks based on large language…
Neural networks have become integral to many fields due to their exceptional performance. The open-source community has witnessed a rapid influx of neural network (NN) repositories with fast-paced iterations, making it crucial for…
Neologism-aware machine translation aims to translate source sentences containing neologisms into target languages. This field remains underexplored compared with general machine translation (MT). In this paper, we propose an agentic…
AI Tool is a large language model (LLM) designed to generate human-like responses in natural language conversations. It is trained on a massive corpus of text from the internet, which allows it to leverage a broad understanding of language,…
Non-volatile Memory (NVM) technologies present a promising alternative to traditional volatile memories such as SRAM and DRAM. Due to the limited availability of real NVM devices, simulators play a crucial role in architectural exploration…
In recent years, Neural Machine Translator (NMT) has shown promise in automatically editing source code. Typical NMT based code editor only considers the code that needs to be changed as input and suggests developers with a ranked list of…
In this paper, we discuss the formalized approach for generating and estimating symbols (and alphabets), which can be communicated by the wide range of non-verbal means based on specific user requirements (medium, priorities, type of…
Answering complex questions that require multi-step multi-type reasoning over raw text is challenging, especially when conducting numerical reasoning. Neural Module Networks(NMNs), follow the programmer-interpreter framework and design…
While hardware-software co-design has significantly improved the efficiency of neural network inference, modeling the training phase remains a critical yet underexplored challenge. Training workloads impose distinct constraints,…
This paper presents DiffMoog - a differentiable modular synthesizer with a comprehensive set of modules typically found in commercial instruments. Being differentiable, it allows integration into neural networks, enabling automated sound…
Neural network interatomic potentials (NNPs) have recently proven to be powerful tools to accurately model complex molecular systems while bypassing the high numerical cost of ab-initio molecular dynamics simulations. In recent years,…