Related papers: Representing Knowledge as Predictions (and State a…
For the past decade, the trajectory of generative artificial intelligence (AI) has been dominated by a model-centric paradigm driven by scaling laws. Despite significant leaps in visual fidelity, this approach has encountered a ``usability…
Weather forecasting is not only a predictive task but an interpretive scientific process requiring explanation, contextualization, and hypothesis generation. This paper introduces AI-Meteorologist, an explainable LLM-agent framework that…
Natural language communication is an intricate and complex process. The speaker usually begins with an intention and motivation of what is to be communicated, and what effects are expected from the communication, while taking into…
Knowledge distillation (KD) has been widely applied in semantic segmentation to compress large models, but conventional approaches primarily preserve in-domain accuracy while neglecting out-of-domain generalization, which is essential under…
Abductive reasoning is the process of making educated guesses to provide explanations for observations. Although many applications require the use of knowledge for explanations, the utilization of abductive reasoning in conjunction with…
Knowledge Graphs (KGs) represent real-world noisy raw information in a structured form, capturing relationships between entities. However, for dynamic real-world applications such as social networks, recommender systems, computational…
When humans perform inductive learning, they often enhance the process with background knowledge. With the increasing availability of well-formed collaborative knowledge bases, the performance of learning algorithms could be significantly…
This paper describes NAIVE, a low-level knowledge representation language and inferencing process. NAIVE has been designed for reasoning about nondeterministic dynamic systems like those found in medicine. Knowledge is represented in a…
Representing words by vectors, or embeddings, enables computational reasoning and is foundational to automating natural language tasks. For example, if word embeddings of similar words contain similar values, word similarity can be readily…
To solve tasks in new environments involving objects unseen during training, agents must reason over prior information about those objects and their relations. We introduce the Prior Knowledge Graph network, an architecture for combining…
Generalizing from individual skill executions to solving long-horizon tasks remains a core challenge in building autonomous agents. A promising direction is learning high-level, symbolic abstractions of the low-level skills of the agents,…
Generative artificial intelligence (AI) systems have transformed various industries by autonomously generating content that mimics human creativity. However, concerns about their social and economic consequences arise with widespread…
Predicting future sensory states is crucial for learning agents such as robots, drones, and autonomous vehicles. In this paper, we couple multiple sensory modalities with exploratory actions and propose a predictive neural network…
Artificial perception is traditionally handled by hand-designing task specific algorithms. However, a truly autonomous robot should develop perceptive abilities on its own, by interacting with its environment, and adapting to new…
We consider the setting of an agent with a fixed body interacting with an unknown and uncertain external world. We show that models trained to predict proprioceptive information about the agent's body come to represent objects in the…
The development of large language models (LLMs) has successfully transformed knowledge-based systems such as open domain question nswering, which can automatically produce vast amounts of seemingly coherent information. Yet, those models…
Deep neural networks implement a sequence of layer-by-layer operations that are each relatively easy to understand, but the resulting overall computation is generally difficult to understand. We consider a simple hypothesis for interpreting…
We introduce the Neural State Machine, seeking to bridge the gap between the neural and symbolic views of AI and integrate their complementary strengths for the task of visual reasoning. Given an image, we first predict a probabilistic…
In the sequential decision making setting, an agent aims to achieve systematic generalization over a large, possibly infinite, set of environments. Such environments are modeled as discrete Markov decision processes with both states and…
When autonomous agents observe different domains of a shared environment, each signal they exchange mixes relevant and irrelevant dimensions. No existing mechanism lets the receiver evaluate which dimensions to absorb. We introduce…