Related papers: Applying AOSE Concepts to Model Crosscutting Varia…
With the rapid development of pre-training technologies, adapting large-scale Vision-Language Models (VLMs) for video understanding \emph{\ie} image-to-video transfer learning has become a dominant paradigm. To achieve superior performance,…
Recent large language models (LLMs) have tended to leverage sparsity to reduce computations, employing the sparsely activated mixture-of-experts (MoE) technique. MoE introduces four modules, including token routing, token communication,…
The scaling of Large Language Models (LLMs) currently faces significant challenges. Model assembly is widely considered a promising solution to break through these performance bottlenecks. However, current ensembling methods are primarily…
Behavioral models are the key enablers for behavioral analysis of Software Product Lines (SPL), including testing and model checking. Active model learning comes to the rescue when family behavioral models are non-existent or outdated. A…
Preference-based reinforcement learning can learn effective reward functions from comparisons, but its scalability is constrained by the high cost of oracle feedback. Lightweight vision-language embedding (VLE) models provide a cheaper…
Test-time adaptation, which enables models to generalize to diverse data with unlabeled test samples, holds significant value in real-world scenarios. Recently, researchers have applied this setting to advanced pre-trained vision-language…
The application of Natural Language Processing (NLP) has achieved a high level of relevance in several areas. In the field of software engineering (SE), NLP applications are based on the classification of similar texts (e.g. software…
Mixture-of-Experts (MoE) architectures employ sparse activation to deliver faster training and inference with higher accuracy than dense LLMs. However, in production serving, MoE models require batch inference to optimize hardware…
Recent work in computer vision and cognitive reasoning has given rise to an increasing adoption of the Violation-of-Expectation (VoE) paradigm in synthetic datasets. Inspired by infant psychology, researchers are now evaluating a model's…
Modern software engineering deals with demanding problems that yield large and complex software. The area of Model-Driven Software Engineering tackles this issue by using models during the development process, but it does not address some…
This paper proposed software architecture for operating an automatic semiconductor manufacturing machine. Recent machines for semiconductor process are required for high level of automation which are composed of motion control, machine…
Large language models frequently exhibit suboptimal performance on low resource languages, primarily due to inefficient subword segmentation and systemic training data imbalances. In this paper, we propose Variable Entropy Policy…
Recent advances in Vision-Language-Action (VLA) models have shown promising capabilities in autonomous driving by leveraging the understanding and reasoning strengths of Large Language Models(LLMs).However, our empirical analysis reveals…
This paper proposes a framework for developing forecasting models by streamlining the connections between core components of the developmental process. The proposed framework enables swift and robust integration of new datasets,…
While Large Language Models (LLMs) excel at reasoning on text and Vision-Language Models (VLMs) are highly effective for visual perception, applying those models for visual instruction-based planning remains a widely open problem. In this…
This paper proposes integrating Aspect-oriented Programming (AOP) into Julia, a language widely used in scientific and High-Performance Computing (HPC). AOP enhances software modularity by encapsulating cross-cutting concerns, such as…
As large language models are increasingly used in high-stakes domains, it is essential that their outputs reflect not average} human preference, rather range of varying perspectives. Achieving such pluralism, however, remains challenging.…
The concept of agile process models has attained great popularity in software (SW) development community in last few years. Agile models promote fast development. Fast development has certain drawbacks, such as weak documentation and…
Release management is one of the most important software processes and is a set of processes that includes the compilation, configuration, and management of software versions in different environments. In recent years, changes in processes,…
Pre-trained Vision-Language (V-L) models set the benchmark for generalization to downstream tasks among the noteworthy contenders. Many characteristics of the V-L model have been explored in existing research including the challenge of the…