Related papers: Composing Copyless Streaming String Transducers

Transformer architectures have achieved remarkable success across language, vision, and multimodal tasks, and there is growing demand for them to address in-context compositional learning tasks. In these tasks, models solve the target…

Voice communication in bandwidth-constrained environments--maritime, satellite, and tactical networks--remains prohibitively expensive. Traditional codecs struggle below 1 kbps, while existing semantic approaches (STT-TTS) sacrifice prosody…

The goal of image style transfer is to render an image with artistic features guided by a style reference while maintaining the original content. Owing to the locality in convolutional neural networks (CNNs), extracting and maintaining the…

In this paper we provide a positive answer to a question left open by Alur and and Deshmukh in 2011 by showing that equivalence of finite-valued copyless streaming string transducers is decidable.

The problem of lossless fixed-rate streaming coding of discrete memoryless sources with side information at the decoder is studied. A random time-varying tree-code is used to sequentially bin strings and a Stack Algorithm with a variable…

In recent years, arbitrary image style transfer has attracted more and more attention. Given a pair of content and style images, a stylized one is hoped that retains the content from the former while catching style patterns from the latter.…

Neural codec language models enable high-quality discrete speech synthesis, yet their inference remains vulnerable to token-level artifacts and distributional drift that degrade perceptual realism. Rather than relying on preference…

Text-guided image and 3D editing have advanced with diffusion-based models, yet methods like Delta Denoising Score often struggle with stability, spatial control, and editing strength. These limitations stem from reliance on complex…

This paper studies reconstruction of strings based upon their substrings spectrum. Under this paradigm, it is assumed that all substrings of some fixed length are received and the goal is to reconstruct the string. While many existing works…

Diffusion models achieve strong generation quality, diversity, and distribution coverage, but their performance often comes with expensive inference. In this work, we propose Stochastic Transition-Map Distillation (STMD), a teacher-free…

Compositional speech-to-speech translation (S2ST) systems built upon speech large language models (SpeechLLMs) have recently shown promising performance. However, existing S2ST systems often either neglect source-language information or…

We introduce the State Stream Transformer (SST), a novel LLM architecture that reveals emergent reasoning behaviours and capabilities latent in pretrained weights through addressing a fundamental limitation in traditional transformer…

Source code summarization aims at generating concise and clear natural language descriptions for programming languages. Well-written code summaries are beneficial for programmers to participate in the software development and maintenance…

We generalize triadic closure, along with previous generalizations of triadic closure, under an intuitive umbrella generalization: the Subgraph-to-Subgraph Transition (SST). We present algorithms and code to model graph evolution in terms…

Streaming Speech-to-Text Translation (StreamST) requires producing translations concurrently with incoming speech, imposing strict latency constraints and demanding models that balance partial-information decision-making with high…

String analysis is the problem of reasoning about how strings are manipulated by a program. It has numerous applications including automatic detection of cross-site scripting (XSS). A popular string analysis technique includes symbolic…

Distributed systems designed to serve clients across the world often make use of geo-replication to attain low latency and high availability. Conflict-free Replicated Data Types (CRDTs) allow the design of predictable multi-master…

The quantity of processed data is crucial for advancing the field of singing voice synthesis. While there are tools available for lyric or note transcription tasks, they all need pre-processed data which is relatively time-consuming (e.g.,…

The class of regular transformations has several equivalent characterizations such as functional MSO transductions, deterministic two-way transducers, streaming string transducers, as well as regular transducer expressions (RTE). For…

Multiparty session types (MPST) provide a rigorous foundation for verifying the safety and liveness of concurrent systems. However, existing approaches often force a difficult trade-off: classical, projection-based techniques are…