Related papers: A Framework for Generating Diverse Haskell-IO Exer…
To efficiently select optimal dataset combinations for enhancing multi-task learning (MTL) performance in large language models, we proposed a novel framework that leverages a neural network to predict the best dataset combinations. The…
Coding agents produce rich trajectories while solving software-engineering tasks. To enable agent self-evolution, these trajectories can be distilled into reusable procedural skills that compactly encode experience to guide future behavior.…
Due to the difficulty of acquiring extensive real-world data, robot simulation has become crucial for parallel training and sim-to-real transfer, highlighting the importance of scalable simulated robotic tasks. Foundation models have…
Automatically generating agentic workflows -- executable operator graphs or codes that orchestrate reasoning, verification, and repair -- has become a practical way to solve complex tasks beyond what single-pass LLM generation can reliably…
Functional languages as input specifications for High-Level Synthesis (HLS) tools allow to specify data dependencies but do not contain a notion of time nor execution order. In this paper, we propose a method to add this notion to the…
Increasing demands in software industry and scarcity of software engineers motivates researchers and practitioners to automate the process of software generation and configuration. Large scale automatic software generation and configuration…
Most meta reinforcement learning (meta-RL) methods learn to adapt to new tasks by directly optimizing the parameters of policies over primitive action space. Such algorithms work well in tasks with relatively slight difference. However,…
Large language models (LLMs) can be used to support software development tasks, e.g., through code completion or code generation. However, their effectiveness drops significantly when considering less popular programming languages such as…
We present a technique to automatically generate search heuristics for dynamic symbolic execution. A key challenge in dynamic symbolic execution is how to effectively explore the program's execution paths to achieve high code coverage in a…
We propose a symbolic generative task description language and a corresponding inference engine capable of representing arbitrary multimodal tasks as structured symbolic flows. Unlike conventional generative models that rely on large-scale…
The open-domain video generation models are constrained by the scale of the training video datasets, and some less common actions still cannot be generated. Some researchers explore video editing methods and achieve action generation by…
Our goal is to assess if AutoML system changes - i.e., to the search space or hyperparameter optimization - will improve the final model's performance on production tasks. However, we cannot test the changes on production tasks. Instead, we…
This article addresses the generation of the ETL operators(Extract-Transform-Load) for supplying a Data Warehouse from a relational data source. As a first step, we add new rules to those proposed by the authors of [1], these rules deal…
Designing effective practice schedules for high-dimensional motor learning tasks remains a challenge, especially when skill states are unobservable and task performance may not reflect the true learning. We propose an automated curriculum…
Large pretrained language models (LMs) have shown impressive In-Context Learning (ICL) ability, where the model learns to do an unseen task via a prompt consisting of input-output examples as the demonstration, without any parameter…
Preparing high-quality instructional materials remains a labor-intensive process that often requires extensive coordination among teaching faculty, instructional designers, and teaching assistants. In this work, we present Instructional…
We formalise the essential data of objective functions as equality constraints on composites of learners. We call these constraints "tasks", and we investigate the idealised view that such tasks determine model behaviours. We develop a…
Nowadays, modeling exercises on software development objects are conducted in higher education institutions for information technology. Not only are there many defects such as missing elements in the models created by learners during the…
We introduce a new unsupervised text embedding method, Meta-Task Prompting with Explicit One-Word Limitation (MetaEOL), for generating high-quality sentence embeddings from Large Language Models (LLMs) without the need for model…
Learning to use tools or objects in common scenes, particularly handling them in various ways as instructed, is a key challenge for developing interactive robots. Training models to generate such manipulation trajectories requires a large…