Related papers: Imperative Learning: A Self-supervised Neuro-Symbo…

While pre-trained language models have obtained state-of-the-art performance for several natural language understanding tasks, they are quite opaque in terms of their decision-making process. While some recent works focus on rationalizing…

Neurosymbolic AI is a growing field of research aiming to combine neural networks learning capabilities with the reasoning abilities of symbolic systems. This hybridization can take many shapes. In this paper, we propose a new formalism for…

Deep learning perception models require a massive amount of labeled training data to achieve good performance. While unlabeled data is easy to acquire, the cost of labeling is prohibitive and could create a tremendous burden on companies or…

Multimodal pretraining is an effective strategy for the trinity of goals of representation learning in autonomous robots: 1) extracting both local and global task progressions; 2) enforcing temporal consistency of visual representation; 3)…

Recent advances in large language models have demonstrated the promise of unsupervised reinforcement learning (RL) methods for enhancing reasoning capabilities without external supervision. However, the generalizability of these label-free…

Foundation model-driven agents often struggle with long-horizon planning due to the transient nature of purely prompting-based reasoning. While existing skill induction methods mitigate this by distilling experience into state-blind…

Classroom AI is rapidly expanding from low-level perception toward higher-level judgments about engagement, confusion, collaboration, and instructional quality. Yet classrooms are among the hardest real-world settings for multimodal vision:…

We present a new AI task and baseline solution for Inter-Subjective Reasoning. We define inter-subjective information, to be a mixture of objective and subjective information possibly shared by different parties. Examples may include…

Recent advances in machine learning, particularly deep learning, have enabled autonomous systems to perceive and comprehend objects and their environments in a perceptual subsymbolic manner. These systems can now perform object detection,…

Adversarial vulnerability and lack of interpretability are critical limitations of deep neural networks, especially in safety-sensitive settings such as autonomous driving. We introduce \DesignII, a neuro-symbolic framework that integrates…

Large Language Models (LLMs) exhibit persistent logical failures in complex reasoning due to the lack of an internal axiomatic framework. We propose Mathesis, a neuro-symbolic architecture that encodes mathematical states as higher-order…

A key objective in the field of artificial intelligence is to develop cognitive models that can exhibit human-like intellectual capabilities. One promising approach to achieving this is through neural-symbolic systems, which combine the…

In robotic manipulation, acquiring samples is extremely expensive because it often requires interacting with the real world. Traditional image-level data augmentation has shown the potential to improve sample efficiency in various machine…

Learning from Demonstration~(LfD) should capture not only how a task is executed, but also its high-level task structure that explains the demonstrated behavior. As robots become more autonomous, such task representations must be…

In this article, we introduce a neuro-symbolic approach that combines a low-level perception task performed by a neural network with a high-level reasoning task performed by a possibilistic rule-based system. The goal is to be able to…

Obtaining large-scale, high-quality reasoning data is crucial for improving the geometric reasoning capabilities of multi-modal large language models (MLLMs). However, existing data generation methods, whether based on predefined tem plates…

Learning-based approaches, such as reinforcement learning (RL) and imitation learning (IL), have indicated superiority over rule-based approaches in complex urban autonomous driving environments, showing great potential to make intelligent…

Self-training is an important technique for solving semi-supervised learning problems. It leverages unlabeled data by generating pseudo-labels and combining them with a limited labeled dataset for training. The effectiveness of…

An interactive instruction following task has been proposed as a benchmark for learning to map natural language instructions and first-person vision into sequences of actions to interact with objects in 3D environments. We found that an…

Incremental Learning (IL) aims to learn new tasks while preserving previously acquired knowledge. Integrating the zero-shot learning capabilities of pre-trained vision-language models into IL methods has marked a significant advancement.…