Related papers: A Framework for Generating Diverse Haskell-IO Exer…
We present a general regularization-based framework for Multi-task learning (MTL), in which the similarity between tasks can be learned or refined using $\ell_p$-norm Multiple Kernel learning (MKL). Based on this very general formulation…
In recent years, Reinforcement Learning (RL), has become a popular field of study as well as a tool for enterprises working on cutting-edge artificial intelligence research. To this end, many researchers have built RL frameworks such as…
As multimodal LLM-driven agents advance in autonomy and generalization, traditional static datasets face inherent scalability limitations and are insufficient for fully assessing their capabilities in increasingly complex and diverse tasks.…
Deep neural networks, despite their remarkable success, remain fundamentally limited in their ability to perform Continual Learning (CL). While most current methods aim to enhance the capabilities of a single model, Inspired by the…
Reinforcement learning is a promising approach for learning control policies for robot tasks. However, specifying complex tasks (e.g., with multiple objectives and safety constraints) can be challenging, since the user must design a reward…
Designing and developing web-enabled remote laboratories for pedagogical purposes is not an easy task. Often, developers (generally, educators who know the subjects they teach but lack of the technical and programming skills required to…
Nowadays, the behavior tree is gaining popularity as a representation for robot tasks due to its modularity and reusability. Designing behavior-tree tasks manually is time-consuming for robot end-users, thus there is a need for…
Automatically generating training supervision for embodied tasks is crucial, as manual designing is tedious and not scalable. While prior works use large language models (LLMs) or vision-language models (VLMs) to generate rewards, these…
Enterprises operate large data lakes using Hadoop and Spark frameworks that (1) run a plethora of tools to automate powerful data preparation/transformation pipelines, (2) run on shared, large clusters to (3) perform many different…
This paper shows how to generate code that efficiently converts sparse tensors between disparate storage formats (data layouts) such as CSR, DIA, ELL, and many others. We decompose sparse tensor conversion into three logical phases:…
When studying software engineering, learning to create UML diagrams is crucial. Similar to how an architect would never build a house without a building plan, designing software architectures is important for developing high-quality…
Short-form videos are gaining popularity in education due to their concise and accessible format that enables microlearning. Yet, most of these videos are manually created. Even for those automatically generated using artificial…
This paper introduces Multidimensional Task Learning (MTL), a unified mathematical framework based on Generalized Einstein MLPs (GE-MLPs) that operate directly on tensors via the Einstein product. We argue that current computer vision task…
Skeleton generation is essential for animating 3D assets, but current deep learning methods remain limited: they cannot handle the growing structural complexity of modern models and offer minimal controllability, creating a major bottleneck…
In-context learning (ICL) describes a language model's ability to generate outputs based on a set of input demonstrations and a subsequent query. To understand this remarkable capability, researchers have studied simplified, stylized…
Visual tasks vary a lot in their output formats and concerned contents, therefore it is hard to process them with an identical structure. One main obstacle lies in the high-dimensional outputs in object-level visual tasks. In this paper, we…
This work presents code to procedurally generate examples for the ARC training tasks. For each of the 400 tasks, an example generator following the transformation logic of the original examples was created. In effect, the assumed underlying…
Task-oriented dialogue systems help users accomplish tasks such as booking a movie ticket and ordering food via conversation. Generative models parameterized by a deep neural network are widely used for next turn response generation in such…
Large-scale pre-trained language models (PLMs) are well-known for being capable of solving a task simply by conditioning a few input-label pairs dubbed demonstrations on a prompt without being explicitly tuned for the desired downstream…
Text generation is a fundamental building block in natural language processing tasks. Existing sequential models performs autoregression directly over the text sequence and have difficulty generating long sentences of complex structures.…