Related papers: Gamora: Graph Learning based Symbolic Reasoning fo…
Humans continue to outperform modern AI systems in their ability to flexibly parse and understand complex visual scenes. Here, we present a novel module for visual reasoning, the Guided Attention Model for (visual) Reasoning (GAMR), which…
Neural networks have emerged as essential components in safety-critical applications -- these use cases demand complex, yet trustworthy computations. Binarized Neural Networks (BNNs) are a type of neural network where each neuron is…
We aim to dismantle the prevalent black-box neural architectures used in complex visual reasoning tasks, into the proposed eXplainable and eXplicit Neural Modules (XNMs), which advance beyond existing neural module networks towards using…
Knowledge graph reasoning is the fundamental component to support machine learning applications such as information extraction, information retrieval, and recommendation. Since knowledge graphs can be viewed as the discrete symbolic…
While Graph Neural Networks (GNNs) are powerful models for learning representations on graphs, most state-of-the-art models do not have significant accuracy gain beyond two to three layers. Deep GNNs fundamentally need to address: 1).…
Graph Chain-of-Thought (Graph-CoT) enables large language models (LLMs) to perform step-by-step reasoning over graph-structured knowledge, but existing pipelines suffer from low accuracy, excessive token usage, high latency, and low…
The move toward artificial intelligence (AI)-native sixth-generation (6G) networks has put more emphasis on the importance of explainability and trustworthiness in network management operations, especially for mission-critical use-cases.…
Recent advances in machine learning have led to a surge in adoption of neural networks for various tasks, but lack of interpretability remains an issue for many others in which an understanding of the features influencing the prediction is…
Neural reasoning accuracy improves when generating intermediate reasoning steps. However, the source of this improvement is yet unclear. Here, we investigate and factorize the benefit of generating intermediate steps for symbolic reasoning.…
Developing models that can learn to reason is a notoriously challenging problem. We focus on reasoning in relational domains, where the use of Graph Neural Networks (GNNs) seems like a natural choice. However, previous work has shown that…
Language agents powered by large language models (LLMs) have demonstrated remarkable capabilities in understanding, reasoning, and executing complex tasks. However, developing robust agents presents significant challenges: substantial…
Recent advances in neural algorithmic reasoning with graph neural networks (GNNs) are propped up by the notion of algorithmic alignment. Broadly, a neural network will be better at learning to execute a reasoning task (in terms of sample…
The importance of building neural networks that can learn to reason has been well recognized in the neuro-symbolic community. In this paper, we apply neural pointer networks for conducting reasoning over symbolic knowledge bases. In doing…
Recent efforts to improve the performance of neural network (NN) accelerators that meet today's application requirements have given rise to a new trend of logic-based NN inference relying on fixed-function combinational logic (FFCL). This…
In order to achieve a general visual question answering (VQA) system, it is essential to learn to answer deeper questions that require compositional reasoning on the image and external knowledge. Meanwhile, the reasoning process should be…
Graph combinatorial optimization (GCO) problems are central to domains like logistics and bioinformatics. While traditional solvers dominate, large language models (LLMs) offer new possibilities for structured reasoning, yet struggle with…
Recently Graph Neural Network (GNN) has been applied successfully to various NLP tasks that require reasoning, such as multi-hop machine reading comprehension. In this paper, we consider a novel case where reasoning is needed over graphs…
Long Chain-of-Thought (LCoT), achieved by Reinforcement Learning with Verifiable Rewards (RLVR), has proven effective in enhancing the reasoning capabilities of Large Language Models (LLMs). However, reasoning in current LLMs is primarily…
The development of artificial intelligence systems with advanced reasoning capabilities represents a persistent and long-standing research question. Traditionally, the primary strategy to address this challenge involved the adoption of…
Which transformer scaling regimes are able to perfectly solve different classes of algorithmic problems? While tremendous empirical advances have been attained by transformer-based neural networks, a theoretical understanding of their…