Related papers: Bridging Control-Centric and Data-Centric Optimiza…
Code understanding and generation have fast become some of the most popular applications of language models (LMs). Nonetheless, research on multilingual aspects of Code-LMs (i.e., LMs for code generation) such as cross-lingual transfer…
The trend towards specialization of software and hardware - fuelled by the end of Moore's law and the still accelerating interest in domain-specific computing, such as machine learning - forces us to radically rethink our compiler designs.…
Traditional control system design, reliant on expert knowledge and precise models, struggles with complex, nonlinear, or uncertain dynamics. This paper introduces AgenticControl, a novel multi-agent framework that automates controller…
Electrical power conversions are common in a large variety of engineering applications. With reference to AC/DC and DC/AC power conversions, a strong research interest resides in multilevel converters, thanks to the many advantages they…
Code-mixed languages, characterized by frequent within-sentence language transitions, present structural challenges that standard language models fail to address. In this work, we propose CMLFormer, an enhanced multi-layer dual-decoder…
We study how the lift-and-project procedure applies to the multiparametric analysis of conic linear optimization (CLO) problems. We first introduce the concept of a pair of primal and dual conic representable sets and define the set-valued…
We present the Distributed and Localized Model Predictive Control (DLMPC) algorithm for large-scale structured linear systems, wherein only local state and model information needs to be exchanged between subsystems for the computation and…
Solving motion tasks autonomously and accurately is a core ability for intelligent real-world systems. To achieve genuine autonomy across multiple systems and tasks, key challenges include coping with unknown dynamics and overcoming the…
Decentralized optimization enables multiple devices to learn a global machine learning model while each individual device only has access to its local dataset. By avoiding the need for training data to leave individual users' devices, it…
Many ML applications and products train on medium amounts of input data but get bottlenecked in real-time inference. When implementing ML systems, conventional wisdom favors segregating ML code into services queried by product code via…
Probabilistic inference is fundamentally hard, yet many tasks require optimization on top of inference, which is even harder. We present a new optimization-via-compilation strategy to scalably solve a certain class of such problems. In…
Traffic-responsive signal control is a cost-effective and easy-to-implement network management strategy with high potential in improving performance in congested networks with dynamic characteristics. Max Pressure (MP) distributed…
Composed image retrieval (CIR) requires multi-modal models to jointly reason over visual content and semantic modifications presented in text-image input pairs. While current CIR models achieve strong performance on common benchmark cases,…
This paper studies class incremental learning (CIL) of continual learning (CL). Many approaches have been proposed to deal with catastrophic forgetting (CF) in CIL. Most methods incrementally construct a single classifier for all classes of…
Model predictive control (MPC) has established itself as the primary methodology for constrained control, enabling general-purpose robot autonomy in diverse real-world scenarios. However, for most problems of interest, MPC relies on the…
Intermediate Representations (IRs) play a critical role in compiler design and program analysis, yet their comprehension by Large Language Models (LLMs) remains underexplored. In this paper, we present an explorative empirical study…
Massive, multi-language, monolithic repositories form the backbone of many modern, complex software systems. To ensure consistent code quality while still allowing fast development cycles, Continuous Integration (CI) is commonly applied.…
Deep learning models require an enormous amount of data for training. However, recently there is a shift in machine learning from model-centric to data-centric approaches. In data-centric approaches, the focus is to refine and improve the…
General-purpose compilers abstract away parallelism, locality, and synchronization, limiting their effectiveness on modern spatial architectures. As modern computing architectures increasingly rely on fine-grained control over data…
We propose a new result-oriented semantic for defining data processing workflows that manipulate data in different semantic forms (files or services) in a unified manner. This approach enables users to define workflows for a vast variety of…