Related papers: ReSyn: A Generalized Recursive Regular Expression …

Expert-level scientific reasoning remains challenging for large language models, particularly on benchmarks such as Humanity's Last Exam (HLE), where rigid tool pipelines, brittle multi-agent coordination, and inefficient test-time scaling…

Split and Rephrase is a text simplification task of rewriting a complex sentence into simpler ones. As a relatively new task, it is paramount to ensure the soundness of its evaluation benchmark and metric. We find that the widely used…

This paper proposes relational program synthesis, a new problem that concerns synthesizing one or more programs that collectively satisfy a relational specification. As a dual of relational program verification, relational program synthesis…

Reactive synthesis transforms a specification of a reactive system, given in a temporal logic, into an implementation. The main advantage of synthesis is that it is automatic. The main disadvantage is that the implementation is usually very…

The use of deep learning techniques has achieved significant progress for program synthesis from input-output examples. However, when the program semantics become more complex, it still remains a challenge to synthesize programs that are…

Time series with missing data are signals encountered in important settings for machine learning. Some of the most successful prior approaches for modeling such time series are based on recurrent neural networks that transform the input and…

Retrieval-augmented generation (RAG) systems trained using reinforcement learning (RL) with reasoning are hampered by inefficient context management, where long, noisy retrieved documents increase costs and degrade performance. We introduce…

Regular expression is important for many natural language processing tasks especially when used to deal with unstructured and semi-structured data. This work focuses on automatically generating regular expressions and proposes a novel…

Recent work has shown that it is possible to resynthesize high-quality speech based, not on text, but on low bitrate discrete units that have been learned in a self-supervised fashion and can therefore capture expressive aspects of speech…

The aim of this work is to address issues where formal specifications cannot be realized on a given dynamical system subjected to a changing environment. Such failures occur whenever the dynamics of the system restrict the robot in such a…

We propose a structured prediction architecture, which exploits the local generic features extracted by Convolutional Neural Networks and the capacity of Recurrent Neural Networks (RNN) to retrieve distant dependencies. The proposed…

We present a neural program synthesis approach integrating components which write, execute, and assess code to navigate the search space of possible programs. We equip the search process with an interpreter or a read-eval-print-loop (REPL),…

This paper presents an efficient speech enhancement (SE) approach that reuses a processing block repeatedly instead of conventional stacking. Rather than increasing the number of blocks for learning deep latent representations, repeating a…

Synthesizer is a type of electronic musical instrument that is now widely used in modern music production and sound design. Each parameters configuration of a synthesizer produces a unique timbre and can be viewed as a unique instrument.…

Sparse autoencoders are usually trained one layer at a time, even though transformer residual stream activations are strongly coupled across depth. This creates a practical problem for multi-layer interventions: different layerwise…

Recent advances in large-scale text-to-image diffusion models (e.g., FLUX.1) have greatly improved visual fidelity in consistent character generation and editing. However, existing methods rarely unify these tasks within a single framework.…

Recent work has proposed a promising approach to improving scalability of program synthesis by allowing the user to supply a syntactic template that constrains the space of potential programs. Unfortunately, creating templates often…

In the synthesis problem, we are given a specification, and we automatically generate a system that satisfies the specification in all environments. We introduce and study {\em synthesis with guided environments} (SGE, for short), where the…

Despite recent advances in inversion and instruction-based image editing, existing approaches primarily excel at editing single, prominent objects but significantly struggle when applied to complex scenes containing multiple entities. To…

Software engineers mainly write code by editing existing programs. In contrast, language models (LMs) autoregressively synthesize programs in a single pass. One explanation for this is the scarcity of sequential edit data. While…