相关论文: InfoCon: Concept Discovery with Generative and Dis…

Multimodal sensory data resembles the form of information perceived by humans for learning, and are easy to obtain in large quantities. Compared to unimodal data, synchronization of concepts between modalities in such data provides…

Text-to-image diffusion models exhibit remarkable generative capabilities, yet their internal operations remain opaque, particularly when handling prompts that are not fully descriptive. In such scenarios, models must make implicit…

Modern generative models demonstrate impressive capabilities, likely stemming from an ability to identify and manipulate abstract concepts underlying their training data. However, fundamental questions remain: what determines the concepts a…

In this paper, we propose a concept learning architecture that enables a robot to build symbols through self-exploration by interacting with a varying number of objects. Our aim is to allow a robot to learn concepts without constraints,…

Interactive intelligent systems, i.e., interactive systems that employ AI technologies, are currently present in many parts of our social, public and political life. An issue reoccurring often in the development of these systems is the…

For machine learning models to be most useful in numerous sociotechnical systems, many have argued that they must be human-interpretable. However, despite increasing interest in interpretability, there remains no firm consensus on how to…

Learning abstractions directly from data is a core challenge in robotics. Humans naturally operate at an abstract level, reasoning over high-level subgoals while delegating execution to low-level motor skills -- an ability that enables…

Existing methods in the Visual Storytelling field often suffer from the problem of generating general descriptions, while the image contains a lot of meaningful contents remaining unnoticed. The failure of informative story generation can…

Image captioning models generally lack the capability to take into account user interest, and usually default to global descriptions that try to balance readability, informativeness, and information overload. On the other hand, VQA models…

This paper describes InfoGAN, an information-theoretic extension to the Generative Adversarial Network that is able to learn disentangled representations in a completely unsupervised manner. InfoGAN is a generative adversarial network that…

We propose a new framework for reasoning about information in complex systems. Our foundation is based on a variational extension of Shannon's information theory that takes into account the modeling power and computational constraints of…

Data science and machine learning provide indispensable techniques for understanding phenomena at scale, but the discretionary choices made when doing this work are often not recognized. Drawing from qualitative research practices, we…

Generative AI research increasingly confronts a shared problem: systems must sustain yet govern their own generative activity when uncertainty is high, evidence is missing, or context is insufficient. This position paper argues that…

Generative AI systems produce meaning with a quality indistinguishable from - and occasionally surpassing - human performance, yet the epistemic mechanism through which this occurs remains poorly understood. This paper argues that…

Feedback in creativity support tools can help crowdworkers to improve their ideations. However, current feedback methods require human assessment from facilitators or peers. This is not scalable to large crowds. We propose Interpretable…

In this work, we investigate a simple and must-known conditional generative framework based on Vector Quantised-Variational AutoEncoder (VQ-VAE) and Generative Pre-trained Transformer (GPT) for human motion generation from textural…

Understanding human behavior is a fundamental goal of social sciences, yet its analysis presents significant challenges. Conventional methodologies employed for the study of behavior, characterized by labor-intensive data collection…

Despite substantial progress in applying neural networks (NN) to multi-agent reinforcement learning (MARL) areas, they still largely suffer from a lack of transparency and interoperability. However, its implicit cooperative mechanism is not…

We are witnessing significant progress on perception models, specifically those trained on large-scale internet images. However, efficiently generalizing these perception models to unseen embodied tasks is insufficiently studied, which will…

Model explanation techniques play a critical role in understanding the source of a model's performance and making its decisions transparent. Here we investigate if explanation techniques can also be used as a mechanism for scientific…