Related papers: Code Reuse With Transformation Objects

Region-based type systems are a powerful tool for various kinds of program analysis. We introduce a new inference algorithm for region types based on an abstract notion of environment transformation. It analyzes the code of a method only…

We propose a way to use a transformer-based language model in conversational speech recognition. Specifically, we focus on decoding efficiently in a weighted finite-state transducer framework. We showcase an approach to lattice re-scoring…

Referring image segmentation is a fundamental vision-language task that aims to segment out an object referred to by a natural language expression from an image. One of the key challenges behind this task is leveraging the referring…

Reference immutability is a type based technique for taming mutation that has long been studied in the context of object-oriented languages, like Java. Recently, though, languages like Scala have blurred the lines between functional…

The UML allows us to specify models in a precise, complete and unambiguous manner. In particular, the UML addresses the specification of all important decisions regarding analysis, design and implementation. Although UML is not a visual…

Language transformations are algorithms that take a language specification in input, and return the language specification modified. Language transformations are useful for automatically adding features such as subtyping to programming…

We devise a unified framework for the design of canonization algorithms. Using hereditarily finite sets, we define a general notion of combinatorial objects that includes graphs, hypergraphs, relational structures, codes, permutation…

Vision encoders are increasingly used in modern applications, from vision-only models to multimodal systems such as vision-language models. Despite their remarkable success, it remains unclear how these architectures represent features…

Automating the conversion of user interface design into code (image-to-code or image-to-UI) is an active area of software engineering research. However, the state-of-the-art solutions do not achieve high fidelity to the original design, as…

Initially developed for natural language processing (NLP), Transformers are now widely used for source code processing, due to the format similarity between source code and text. In contrast to natural language, source code is strictly…

Learning meaningful and general representations from unannotated speech that are applicable to a wide range of tasks remains challenging. In this paper we propose to use autoregressive predictive coding (APC), a recently proposed…

Language models now provide an interface to express and often solve general problems in natural language, yet their ultimate computational capabilities remain a major topic of scientific debate. Unlike a formal computer, a language model is…

Reliable perception is fundamental for safety critical decision making in autonomous driving. Yet, vision based object detector neural networks remain vulnerable to uncertainty arising from issues such as data bias and distributional…

In modern OCaml, single-argument datatype declarations (variants with a single constructor, records with a single field) can sometimes be `unboxed'. This means that their memory representation is the same as their single argument (omitting…

Recent studies have demonstrated the effectiveness of position encoding in transformer architectures. By incorporating positional information, this approach provides essential guidance for modeling dependencies between elements across…

We investigate latent-space scalability for multi-task collaborative intelligence, where one of the tasks is object detection and the other is input reconstruction. In our proposed approach, part of the latent space can be selectively…

In functional programming, datatypes a la carte provide a convenient modular representation of recursive datatypes, based on their initial algebra semantics. Unfortunately it is highly challenging to implement this technique in proof…

C++, Java, C#, Python, Ruby, JavaScript are the most powerful object-oriented programming languages, if language power would be defined as the number of features available for a programmer. EO, on the other hand, is an object-oriented…

Continual Learning (CL) involves training a machine learning model in a sequential manner to learn new information while retaining previously learned tasks without the presence of previous training data. Although there has been significant…

There is often a sort of a protocol associated to each class, stating when and how certain methods should be called. Given that this protocol is, if at all, described in the documentation accompanying the class, current mainstream…