Related papers: KOALA: a Configurable Tool for Collecting IDE Data…
Collecting a high-quality dataset is a critical task that demands meticulous attention to detail, as overlooking certain aspects can render the entire dataset unusable. Autonomous driving challenges remain a prominent area of research,…
Transfer learning is a proven technique in 2D computer vision to leverage the large amount of data available and achieve high performance with datasets limited in size due to the cost of acquisition or annotation. In 3D, annotation is known…
Personalized medicine remains a major challenge for scientists. The rapid growth of Machine learning and Deep learning has made them a feasible al- ternative for predicting the most appropriate therapy for individual patients. However, the…
One of the central tasks in software maintenance is being able to understand and develop code changes. Thus, given a natural language description of the desired new operation of a function, an agent (human or AI) might be asked to generate…
The generation of large, high-quality datasets for code understanding and generation remains a significant challenge, particularly when aligning decompiled binaries with their original source code. To address this, we present CodableLLM, a…
We study the design decisions of publicly available instruction tuning methods, and break down the development of Flan 2022 (Chung et al., 2022). Through careful ablation studies on the Flan Collection of tasks and methods, we tease apart…
With the continuous progress of visual generation technologies, the scale of video datasets has grown exponentially. The quality of these datasets plays a pivotal role in the performance of video generation models. We assert that temporal…
Machine learning (ML) is nowadays widely used for different purposes and in several disciplines. From self-driving cars to automated medical diagnosis, machine learning models extensively support users' daily activities, and software…
As text-to-image (T2I) synthesis models increase in size, they demand higher inference costs due to the need for more expensive GPUs with larger memory, which makes it challenging to reproduce these models in addition to the restricted…
The ability to adapt to unseen, local contexts is an important challenge that successful models of source code must overcome. One of the most popular approaches for the adaptation of such models is dynamic evaluation. With dynamic…
General Continual Learning (GCL) aims at learning from non independent and identically distributed stream data without catastrophic forgetting of the old tasks that don't rely on task boundaries during both training and testing stages. We…
Class-incremental learning (CIL) enables models to learn new classes progressively while preserving knowledge of previously learned ones. Recent advances in this field have shifted towards parameter-efficient fine-tuning techniques, with…
Rehearsal approaches in class incremental learning (CIL) suffer from decision boundary overfitting to new classes, which is mainly caused by two factors: insufficiency of old classes data for knowledge distillation and imbalanced data…
Traditional code instruction data synthesis methods suffer from limited diversity and poor logic. We introduce Infinite-Instruct, an automated framework for synthesizing high-quality question-answer pairs, designed to enhance the code…
Long video question answering is a challenging task that involves recognizing short-term activities and reasoning about their fine-grained relationships. State-of-the-art video Large Language Models (vLLMs) hold promise as a viable solution…
GitHub Copilot is an artificial intelligence model for automatically generating source code from natural language problem descriptions. Since June 2022, Copilot has officially been available for free to all students as a plug-in to…
Document layout analysis (DLA) aims to divide a document image into different types of regions. DLA plays an important role in the document content understanding and information extraction systems. Exploring a method that can use less data…
Large language models (LLMs) have shown impressive promise in code generation, yet their progress remains limited by the shortage of large-scale datasets that are both diverse and well-aligned with human reasoning. Most existing resources…
This paper presents an AI-assisted programming tool called Copilot for Xcode for program composition and design to support human software developers. By seamlessly integrating cloud-based Large Language Models (LLM) with Apple's local…
Academia and industry have developed several platforms to support the popular privacy-preserving distributed learning method -- Federated Learning (FL). However, these platforms are complex to use and require a deep understanding of FL,…