Related papers: Combining Example-Based and Rule-Based Program Tra…

Model merging leverages multiple finetuned expert models to construct a multi-task model with low cost, and is gaining increasing attention. However, as a growing number of finetuned models become publicly available, concerns about the…

Advancing beyond single monolithic language models (LMs), recent research increasingly recognizes the importance of model collaboration, where multiple LMs collaborate, compose, and complement each other. Existing research on this topic has…

Multi-task model merging offers an efficient solution for integrating knowledge from multiple fine-tuned models, mitigating the significant computational and storage demands associated with multi-task training. As a key technique in this…

Knowledge conflict arises from discrepancies between information in the context of a large language model (LLM) and the knowledge stored in its parameters. This can hurt performance when using standard decoding techniques, which tend to…

Design of large software systems requires rigorous application of software engineering methods covering all phases of the software process. Debugging during the early design phases is extremely important, because late bug-fixes are…

Software systems endure many noteworthy changes throughout their life-cycle in order to follow the evolution of the problem domains. Generally, the software system architecture cannot follow the rapid evolution of a problem domain which…

In this paper, we propose a procedure for designing controlled test problems for single-objective bilevel optimization. The construction procedure is flexible and allows its user to control the different complexities that are to be included…

Training a deep learning model on source code has gained significant traction recently. Since such models reason about vectors of numbers, source code needs to be converted to a code representation before vectorization. Numerous approaches…

Discovering a solution in a combinatorial space is prevalent in many real-world problems but it is also challenging due to diverse complex constraints and the vast number of possible combinations. To address such a problem, we introduce a…

Software bugs require developers to exert significant effort to identify and resolve them, often consuming about one-third of their time. Bug localization, the process of pinpointing the exact source code files that need modification, is…

Model merging has emerged as an efficient technique for expanding large language models (LLMs) by integrating specialized expert models. However, it also introduces a new threat: model merging stealing, where free-riders exploit models…

Resolving conflicts is critical for improving the reliability of multi-view classification. While prior work focuses on learning consistent and informative representations across views, it often assumes perfect alignment and equal…

Recent works have investigated the problem of the conflict redistribution in the fusion rules of evidence theories. As a consequence of these works, many new rules have been proposed. Now, there is not a clear theoretical criterion for a…

Cognitive control, the ability to coordinate competing information sources in pursuit of goals, is fundamental to intelligent behavior. We systematically investigate whether Vision Language Models (VLMs) exhibit cognitive control and how…

Architecture erosion (AEr) can adversely affect software development and has received significant attention in the last decade. However, there is an absence of a comprehensive understanding of the state of research about the reasons and…

For decision making under uncertainty, min-max regret has been established as a popular methodology to find robust solutions. In this approach, we compare the performance of our solution against the best possible performance had we known…

Large language models can generate useful code from natural language, but their outputs come without correctness guarantees. Verifiable code generation offers a path beyond testing by requiring models to produce not only executable code,…

Causal-consistent reversible debugging allows one to explore concurrent computations back and forth in order to locate the source of an error. In this setting, backward steps can be chosen freely as long as they are "causal consistent",…

Software testing is a critical aspect of software development, yet generating test cases remains a routine task for engineers. This paper presents a benchmark, CLOVER, to evaluate models' capabilities in generating and completing test cases…

Collaborative working is increasingly popular, but it presents challenges due to the need for high responsiveness and disconnected work support. To address these challenges the data is optimistically replicated at the edges of the network,…