相关论文: Paired Comparisons-based Interactive Differential …
Retrieval-augmented generation (RAG) grounds large language models with external evidence, but under a limited context budget, the key challenge is deciding which retrieved passages should be injected. We show that retrieval relevance…
Automated test case generation has proven to be useful to reduce the usually high expenses of software testing. However, several studies have also noted the skepticism of testers regarding the comprehension of generated test suites when…
In computer interfaces in general, especially in information retrieval tasks, it is important to be able to quickly find and retrieve information. State of the art approach, used, for example, in search engines, is not effective as it…
Information Retrieval (IR) evaluation involves far more complexity than merely presenting performance measures in a table. Researchers often need to compare multiple models across various dimensions, such as the Precision-Recall trade-off…
Evolutionary game theory has been widely used to study the evolution of cooperation in social dilemmas where imitation-led strategy updates are typically assumed. However, results of recent behavioral experiments are not compatible with the…
Differential Evolution (DE) is a widely used evolutionary algorithm for black-box optimization problems. However, in modern DE implementations, a major challenge lies in the limited population diversity caused by the fixed population size…
Federated learning enables a large amount of edge computing devices to jointly learn a model without data sharing. As a leading algorithm in this setting, Federated Averaging (\texttt{FedAvg}) runs Stochastic Gradient Descent (SGD) in…
LLM-empowered multi-agent systems offer new potential to accelerate scientific discovery by generating novel research ideas. However, existing methods typically coordinate agents through temporary texts, such as drafts or chat logs; it is…
Dynamic optimization, for which the objective functions change over time, has attracted intensive investigations due to the inherent uncertainty associated with many real-world problems. For its robustness with respect to noise,…
Many science and engineering applications require finding solutions to planning and optimization problems by satisfying a set of constraints. These constraint problems (CPs) are typically NP-complete and can be formalized as constraint…
Many applications seek to optimize LLM outputs at test time by iteratively proposing, scoring, and refining candidates over a discrete output space. Existing methods use a calibrated scalar evaluator for the target objective to guide…
The development of mobile communication technology, hardware, distributed computing, and artificial intelligence (AI) technology has promoted the application of edge computing in the field of heterogeneous Internet of Things (IoT). In order…
Federated learning has been widely applied to enable decentralized devices, which each have their own local data, to learn a shared model. However, learning from real-world data can be challenging, as it is rarely identically and…
Complex data analysis inherently seeks unexpected insights through exploratory visual analysis methods, transcending logical, step-by-step processing. However, existing interfaces such as notebooks and dashboards have limitations in…
This paper presents Automatic Algorithm Discoverer (AAD), an evolutionary framework for synthesizing programs of high complexity. To guide evolution, prior evolutionary algorithms have depended on fitness (objective) functions, which are…
Existing methods for explainable artificial intelligence (XAI), including popular feature importance measures such as SAGE, are mostly restricted to the batch learning scenario. However, machine learning is often applied in dynamic…
In this paper, we propose Shallow Aggressive Decoding (SAD) to improve the online inference efficiency of the Transformer for instantaneous Grammatical Error Correction (GEC). SAD optimizes the online inference efficiency for GEC by two…
Deep ensembles perform better than a single network thanks to the diversity among their members. Recent approaches regularize predictions to increase diversity; however, they also drastically decrease individual members' performances. In…
Automated feature engineering (AutoFE) is the process of automatically building and selecting new features that help improve downstream predictive performance. While traditional feature engineering requires significant domain expertise and…
The high-performance generative artificial intelligence (GAI) represents the latest evolution of computational intelligence, while the blessing of future 6G networks also makes edge intelligence (EI) full of development potential. The…