Related papers: ReSyn: A Generalized Recursive Regular Expression …
Reactive synthesis is a paradigm for automatically building correct-by-construction systems that interact with an unknown or adversarial environment. We study how to do reactive synthesis when part of the specification of the system is that…
The ability to compositionally map language to referents, relations, and actions is an essential component of language understanding. The recent gSCAN dataset (Ruis et al. 2020, NeurIPS) is an inspiring attempt to assess the capacity of…
A widely adopted strategy for model enhancement is to use synthetic data generated by a stronger model for supervised fine-tuning (SFT). However, for emerging reasoning models like Qwen3-8B, this approach often fails to improve reasoning…
In formal synthesis of reactive systems an implementation of a system is automatically constructed from its formal specification. The great advantage of synthesis is that the resulting implementation is correct by construction; therefore…
To address a looming crisis of unreproducible evaluation for named entity recognition, we propose guidelines and introduce SeqScore, a software package to improve reproducibility. The guidelines we propose are extremely simple and center…
This paper describes an efficient algorithm REx for generating symbolic rules from artificial neural network (ANN). Classification rules are sought in many areas from automatic knowledge acquisition to data mining and ANN rule extraction.…
Studies on generalization performance of machine learning algorithms under the scope of information theory suggest that compressed representations can guarantee good generalization, inspiring many compression-based regularization methods.…
Reactive synthesis aims at automatic construction of systems from their behavioural specifications. The research mostly focuses on synthesis of systems dealing with Boolean signals. But real-life systems are often described using…
Regular expression (regex) matching is fundamental in many applications, especially in web services. However, matching by backtracking -- preferred by most real-world implementations for its practical performance and backward compatibility…
We present a method for synthesizing recursive functions that satisfy both a functional specification and an asymptotic resource bound. Prior methods for synthesis with a resource metric require the user to specify a concrete expression…
Large language models and agents have achieved remarkable progress in code generation. However, existing benchmarks focus on isolated function/class-level generation (e.g., ClassEval) or modifications to existing codebases (e.g.,…
PEGs are a formal grammar foundation for describing syntax, and are not hard to generate parsers with a plain recursive decent parsing. However, the large amount of C-stack consumption in the recursive parsing is not acceptable especially…
Sequential Recommender Systems (SRSs) have emerged as a highly efficient approach to recommendation systems. By leveraging sequential data, SRSs can identify temporal patterns in user behaviour, significantly improving recommendation…
Software configurations play a crucial role in determining the behavior of software systems. In order to ensure safe and error-free operation, it is necessary to identify the correct configuration, along with their valid bounds and rules,…
The goal of decompilation is to convert compiled low-level code (e.g., assembly code) back into high-level programming languages, enabling analysis in scenarios where source code is unavailable. This task supports various reverse…
Generative Adversarial Networks (GANs) have seen steep ascension to the peak of ML research zeitgeist in recent years. Mostly catalyzed by its success in the domain of image generation, the technique has seen wide range of adoption in a…
Most work on query optimization has concentrated on loop-free queries. However, data science and machine learning workloads today typically involve recursive or iterative computation. In this work, we propose a novel framework for…
Ensemble learning has proven effective in boosting predictive performance, but traditional methods such as bagging, boosting, and dynamic ensemble selection (DES) suffer from high computational cost and limited adaptability to heterogeneous…
Matching regexes (regular expressions) is a common problem in many areas of computer science, with requirements on high speed and robust performance. Regexes with backreferences allow one to express certain patterns (even beyond regular)…
We present a new model for singing synthesis based on a modified version of the WaveNet architecture. Instead of modeling raw waveform, we model features produced by a parametric vocoder that separates the influence of pitch and timbre.…