Related papers: Dreaming in Code for Curriculum Learning in Open-E…
Large Language Model (LLM) agents trained with reinforcement learning (RL) show great promise for solving complex, multi-step tasks. However, their performance is often crippled by "Context Explosion", where the accumulation of long text…
Despite impressive progress in video generation, existing models remain limited to surface-level plausibility, lacking a coherent and unified understanding of the world. Prior approaches typically incorporate only a single form of…
As the landscape of software engineering evolves, introductory programming courses must go beyond teaching syntax to foster comprehensive technical competencies and professional soft skills. This paper reports on a pedagogical experience in…
Intelligent and reliable task planning is a core capability for generalized robotics, requiring a descriptive domain representation that sufficiently models all object and state information for the scene. We present CLIMB, a continual…
While great strides have been made in using deep learning algorithms to solve supervised learning tasks, the problem of unsupervised learning - leveraging unlabeled examples to learn about the structure of a domain - remains a difficult…
The backpropagation of error algorithm used to train deep neural networks has been fundamental to the successes of deep learning. However, it requires sequential backward updates and non-local computations, which make it challenging to…
Computing Education faces significant challenges in equipping graduates with the resilience necessary to remain relevant amid rapid technological change. While existing curricula cultivate computing competencies, they often fail to…
A lot of recent machine learning research papers have ``open-ended learning'' in their title. But very few of them attempt to define what they mean when using the term. Even worse, when looking more closely there seems to be no consensus on…
Deep learning, a branch of artificial intelligence, is a data-driven method that uses multiple layers of interconnected units or neurons to learn intricate patterns and representations directly from raw input data. Empowered by this…
The introductory programming sequence has been the focus of much research in computing education. The recent advent of several viable and freely-available AI-driven code generation tools present several immediate opportunities and…
Complex 3D scene understanding has gained increasing attention, with scene encoding strategies playing a crucial role in this success. However, the optimal scene encoding strategies for various scenarios remain unclear, particularly…
Nowadays service robots are leaving the structured and completely known environments and entering human-centric settings. For these robots, object perception and grasping are two challenging tasks due to the high demand for accurate and…
To interact effectively with humans in the real world, it is important for agents to understand language that describes the dynamics of the environment--that is, how the environment behaves--rather than just task instructions specifying…
We present Dream-Coder 7B, an open-source discrete diffusion language model for code generation that exhibits emergent any-order generation capabilities. Unlike traditional autoregressive (AR) models that decode strictly left-to-right,…
We introduce KodCode, a synthetic dataset that addresses the persistent challenge of acquiring high-quality, verifiable training data across diverse difficulties and domains for training Large Language Models for coding. Existing…
Distribution shift has been a longstanding challenge for the reliable deployment of deep learning (DL) models due to unexpected accuracy degradation. Although DL has been becoming a driving force for large-scale source code analysis in the…
Modern software systems continuously undergo code upgrades to enhance functionality, security, and performance, and Large Language Models (LLMs) have demonstrated remarkable capabilities in code migration tasks. However, while research on…
While deep neural networks have led to human-level performance on computer vision tasks, they have yet to demonstrate similar gains for holistic scene understanding. In particular, 3D context has been shown to be an extremely important cue…
We extend the framework of efficient coding, which has been used to model the development of sensory processing in isolation, to model the development of the perception/action cycle. Our extension combines sparse coding and reinforcement…
The capacity of an embodied agent to understand, predict, and interact with its environment is fundamentally contingent on an internal world model. This paper introduces a novel framework for investigating the formation and adaptation of…