Related papers: Solving the TTC 2011 Reengineering Case with VIATR…
Can we teach natural language understanding models to track their beliefs through intermediate points in text? We propose a representation learning framework called breakpoint modeling that allows for learning of this type. Given any text…
Formats for representing and manipulating verification problems are extremely important for supporting the ecosystem of tools, developers, and practitioners. A good format allows representing many different types of problems, has a strong…
Transformers have had a significant impact on natural language processing and have recently demonstrated their potential in computer vision. They have shown promising results over convolution neural networks in fundamental computer vision…
Future service robots working in human environments, such as kitchens, will face situations where they need to improvise. The usual tool for a given task might not be available and the robot will have to use some substitute tool. The robot…
For a company looking to provide delightful user experiences, it is of paramount importance to take care of any customer issues. This paper proposes COTA, a system to improve speed and reliability of customer support for end users through…
In this paper, we present our solution for the WSDM2023 Toloka Visual Question Answering Challenge. Inspired by the application of multimodal pre-trained models to various downstream tasks(e.g., visual question answering, visual grounding,…
In this paper, we focus on the design and verification of timed automata (TA). We introduce a new method for assisting construction and verification of TA models along with a tool implementing the proposed method, i.e., ATAC: Automated…
This paper contains details on the algorithms implemented in the TEMPO2 pulsar timing software package and describes how the software is used. Information is given on how to download and install the software, use the various interfaces,…
We introduce TD-Interpreter, a specialized ML tool that assists engineers in understanding complex timing diagrams (TDs), originating from a third party, during their design and verification process. TD-Interpreter is a visual…
Two key issues hindering the transition towards FAIR data science are the poor discoverability and inconsistent instructions for the use of data extractor tools, i.e., how we go from raw data files created by instruments, to accessible…
How do vision transformers (ViTs) represent and process the world? This paper addresses this long-standing question through the first systematic analysis of 6.6K features across all layers, extracted via sparse autoencoders, and by…
Numerical reasoning over table-and-text hybrid passages, such as financial reports, poses significant challenges and has numerous potential applications. Noise and irrelevant variables in the model input have been a hindrance to its…
In this technical report, we present our solutions to the Traffic4cast 2022 core challenge and extended challenge. In this competition, the participants are required to predict the traffic states for the future 15-minute based on the…
Modern spreadsheet systems can be used to implement complex spreadsheet applications including data sheets, customized user forms and executable procedures written in a scripting language. These applications are often developed by…
To refactor already working code while keeping reliability, compatibility and perhaps security, we can borrow ideas from micropass/nanopass compilers. By treating the procedure of software refactoring as composing code transformations, and…
This paper introduces TransDreamerV3, a reinforcement learning model that enhances the DreamerV3 architecture by integrating a transformer encoder. The model is designed to improve memory and decision-making capabilities in complex…
The purpose of this article is to describe an adaptive decision-making support model aimed at improving the efficiency of engineering infrastructure reconstruction program management in the context of developing the architecture and work…
The first objective of this paper is to present and discuss various types of models of program understanding. They are discussed in relation to models of text understanding. The second objective of this paper is to assess the effect of…
Test-time reinforcement learning (TTRL) has emerged as a promising paradigm for self-evolving large reasoning models (LRMs), enabling online adaptation on unlabeled test inputs via self-induced rewards through majority voting. However, a…
The current trends in next-generation exascale systems go towards integrating a wide range of specialized (co-)processors into traditional supercomputers. Due to the efficiency of heterogeneous systems in terms of Watts and FLOPS per…