Related papers: Ensuring Reliability via Hyperparameter Selection:…

Effective model and hyperparameter selection remains a major challenge in deep learning, often requiring extensive expertise and computation. While AutoML and large language models (LLMs) promise automation, current LLM-based approaches…

Large language models (LLMs) have achieved notable progress. Despite their success, next-token prediction (NTP), the dominant method for LLM training and inference, is constrained in both contextual coverage and inference efficiency due to…

The performance of modern machine learning methods highly depends on their hyperparameter configurations. One simple way of selecting a configuration is to use default settings, often proposed along with the publication and implementation…

Fine-tuning large language models for different tasks can be costly and inefficient, and even methods that reduce the number of tuned parameters still require full gradient-based optimization. We propose HyperTuning, a novel approach to…

In software engineering, the meticulous configuration of software tools is crucial in ensuring optimal performance within intricate systems. However, the complexity inherent in selecting optimal configurations is exacerbated by the…

Multi-task learning (MTL) is a machine learning paradigm that aims to improve the generalization performance of a model on multiple related tasks by training it simultaneously on those tasks. Unlike MTL, where the model has instant access…

Large language models (LLMs) distinguish themselves from previous technologies by functioning as collaborative ``thought partners,'' capable of engaging more fluidly in natural language on a range of tasks. As LLMs increasingly influence…

Identifying logical errors in complex, incomplete or even contradictory and overall heterogeneous data like students' experimentation protocols is challenging. Recognizing the limitations of current evaluation methods, we investigate the…

Neural networks are increasingly used to support decision-making. To verify their reliability and adaptability, researchers and practitioners have proposed a variety of tools and methods for tasks such as NN code verification, refactoring,…

The launch of ChatGPT by OpenAI in November 2022 marked a pivotal moment for Artificial Intelligence, introducing Large Language Models (LLMs) to the mainstream and setting new records in user adoption. LLMs, particularly ChatGPT, trained…

As large language models (LLMs) are increasingly deployed in high-stakes settings, the risk of generating harmful or toxic content remains a central challenge. Post-hoc alignment methods are brittle: once unsafe patterns are learned during…

Self-Supervised Learning (SSL) has become a very active area of Deep Learning research where it is heavily used as a pre-training method for classification and other tasks. However, the rapid pace of advancements in this area comes at a…

This paper investigates the challenges and potential solutions for improving machine learning systems for low-resource languages. State-of-the-art models in natural language processing (NLP), text-to-speech (TTS), speech-to-text (STT), and…

Deep text matching approaches have been widely studied for many applications including question answering and information retrieval systems. To deal with a domain that has insufficient labeled data, these approaches can be used in a…

Large Language Models (LLMs) are rapidly reshaping machine translation (MT), particularly by introducing instruction-following, in-context learning, and preference-based alignment into what has traditionally been a supervised…

A Reinforcement Learning (RL) system depends on a set of initial conditions (hyperparameters) that affect the system's performance. However, defining a good choice of hyperparameters is a challenging problem. Hyperparameter tuning often…

With the release of ChatGPT and other large language models (LLMs) the discussion about the intelligence, possibilities, and risks, of current and future models have seen large attention. This discussion included much debated scenarios…

Many machine learning and data mining algorithms rely on the assumption that the training and testing data share the same feature space and distribution. However, this assumption may not always hold. For instance, there are situations where…

Neural networks dominate the modern machine learning landscape, but their training and success still suffer from sensitivity to empirical choices of hyperparameters such as model architecture, loss function, and optimisation algorithm. In…

There is a growing interest on formal methods-based robotic planning for temporal logic objectives. In this work, we extend the scope of existing synthesis methods to hyper-temporal logics. We are motivated by the fact that important…