Related papers: Eliom: A Language for Modular Tierless Web Program…

Language model intelligence is revolutionizing the way we program materials simulations. However, the diversity of simulation scenarios renders it challenging to precisely transform human language into a tailored simulator. Here, using…

Emotional text-to-speech (E-TTS) is central to creating natural and trustworthy human-computer interaction. Existing systems typically rely on sentence-level control through predefined labels, reference audio, or natural language prompts.…

The continued improvements in language model capability have unlocked their widespread use as drivers of autonomous agents, for example in coding or computer use applications. However, the core of these systems has not changed much since…

Large language model (LLM) serving infrastructures are undergoing a shift toward heterogeneity and disaggregation. Modern deployments increasingly integrate diverse accelerators and near-memory processing technologies, introducing…

There has been a widespread emergence of computing devices in the past few years that go beyond the capabilities of traditional desktop computers. However, users want to use the same kinds of applications and access the same data and…

Recent advances in large language models (LLMs) have demonstrated strong performance in generating code for general-purpose programming languages. However, their potential for hardware description languages (HDLs), such as SystemVerilog,…

The reasoning capabilities of the recent LLMs enable them to execute external function calls to overcome their inherent limitations, such as knowledge cutoffs, poor arithmetic skills, or lack of access to private data. This development has…

This research proposes a language independent intra-process framework for object based composition of unmodified code modules. Intuitively, the two major programming models, threads and processes, can be considered as extremes along a…

Large Language Models (LLMs) have become increasingly capable of handling diverse tasks with the aid of well-crafted prompts and integration of external tools, but as task complexity rises, the workflow involving LLMs can be complicated and…

Creating suitable diagrams for technical and scientific publications is challenging and time-consuming, as manual control over the layout is required to communicate information effectively. Existing diagramming tools usually allow modeling…

Designing low-latency cloud-based applications that are adaptable to unpredictable workloads and efficiently utilize modern cloud computing platforms is hard. The actor model is a popular paradigm that can be used to develop distributed…

This paper introduces SAIL, a single transformer unified multimodal large language model (MLLM) that integrates raw pixel encoding and language decoding within a singular architecture. Unlike existing modular MLLMs, which rely on a…

Template-based and LLM-based code generation are both key enablers of automated software development. The former provides correctness guarantees but are rigid for complex requirements, whereas LLMs offer high flexibility at the risk of…

Tool learning has emerged as a crucial capability for large language models (LLMs) to solve complex real-world tasks through interaction with external tools. Existing approaches face significant challenges, including reliance on…

In this work, we address question answering (QA) over a hybrid of tabular and textual data that are very common content on the Web (e.g. SEC filings), where discrete reasoning capabilities are often required. Recently, large language models…

Modeling interoperability between programs in different languages is a key problem when modeling verified and secure compilation, which has been successfully addressed using multi-language semantics. Unfortunately, existing models of…

Large Language Models (LLMs) have demonstrated impressive capabilities in language generation and general task performance. However, their application to spoken language understanding (SLU) remains challenging, particularly for token-level…

We present Reelay, a unified online temporal logic monitoring framework designed for the rigorous analysis and runtime verification of cyber-physical systems. Reelay addresses the fragmentation of existing logical formalisms and tools by…

Publish/subscribe systems play a key role in enabling communication between numerous devices in distributed and large-scale architectures. While widely adopted, securing such systems often trades portability for additional integrity and…

Serverless computing paradigm has become more ingrained into the industry, as it offers a cheap alternative for application development and deployment. This new paradigm has also created new kinds of problems for the developer, who needs to…