Related papers: Learning How to Search: Generating Effective Test …
We propose a novel adaptive approximation approach for test-time resource-constrained prediction. Given an input instance at test-time, a gating function identifies a prediction model for the input among a collection of models. Our…
Adaptive Retrieval-Augmented Generation aims to mitigate the interference of extraneous noise by dynamically determining the necessity of retrieving supplementary passages. However, as Large Language Models evolve with increasing robustness…
The objective of a reinforcement learning agent is to discover better actions through exploration. However, typical exploration techniques aim to maximize rewards, often incurring high costs in both exploration and learning processes. We…
Checklists are simple decision aids that are often used to promote safety and reliability in clinical applications. In this paper, we present a method to learn checklists for clinical decision support. We represent predictive checklists as…
Programming based approaches to reasoning tasks have substantially expanded the types of questions models can answer about visual scenes. Yet on benchmark visual reasoning data, when models answer correctly, they produce incorrect programs…
In recent years, Evolutionary Algorithms (EAs) have frequently been adopted to evolve instances for optimization problems that pose difficulties for one algorithm while being rather easy for a competitor and vice versa. Typically, this is…
The success of the application of machine-learning techniques to compilation tasks can be largely attributed to the recent development and advancement of program characterization, a process that numerically or structurally quantifies a…
Verifiers or reward models are often used to enhance the reasoning performance of large language models (LLMs). A common approach is the Best-of-N method, where N candidate solutions generated by the LLM are ranked by a verifier, and the…
Hard optimisation problems such as Boolean Satisfiability typically have long solving times and can usually be solved by many algorithms, although the performance can vary widely in practice. Research has shown that no single algorithm…
Foundation models contain a wealth of information from their vast number of training samples. However, most prior arts fail to extract this information in a precise and efficient way for small sample sizes. In this work, we propose a…
Generating tests for games is challenging due to the high degree of randomisation inherent to games and hard-to-reach program states that require sophisticated gameplay. The test generator NEATEST tackles these challenges by combining…
Selecting the most relevant or informative features is a key issue in actual machine learning problems. Since an exhaustive search is not feasible even for a moderate number of features, an intelligent search strategy must be employed for…
Recent advancements in instruction tuning for large language models (LLMs) suggest that a small, high-quality dataset can significantly equip LLMs with instruction-following capabilities, outperforming large datasets often burdened by…
Automatically generating test suites is intrinsically a multi-objective problem, as any of the testing targets (e.g, statements to execute or mutants to kill) is an objective on its own. Test suite generation has peculiarities that are…
The balance between convergence and diversity is a key issue of evolutionary multi-objective optimization. The recently proposed stable matching-based selection provides a new perspective to handle this balance under the framework of…
We propose a genetic algorithm (GA) based method for modifying n-best lists produced by a machine translation (MT) system. Our method offers an innovative approach to improving MT quality and identifying weaknesses in evaluation metrics.…
The training of generative adversarial networks (GANs) is usually vulnerable to mode collapse and vanishing gradients. The evolutionary generative adversarial network (E-GAN) attempts to alleviate these issues by optimizing the learning…
Decoding from the output distributions of large language models to produce high-quality text is a complex challenge in language modeling. Various approaches, such as beam search, sampling with temperature, $k-$sampling, nucleus…
GTFLAT, as a game theory-based add-on, addresses an important research question: How can a federated learning algorithm achieve better performance and training efficiency by setting more effective adaptive weights for averaging in the model…
We propose an instance-wise adaptive sampling framework for constructing compact and informative training datasets for supervised learning of inverse problem solutions. Typical learning-based approaches aim to learn a general-purpose…