相关论文: Operational Latent Spaces

Suppose we want to build a system that answers a natural language question by representing its semantics as a logical form and computing the answer given a structured database of facts. The core part of such a system is the semantic parser…

Large Language Models (LLMs) excel at capturing latent semantics and contextual relationships across diverse modalities. However, in modeling user behavior from sequential interaction data, performance often suffers when such semantic…

Ordinal data analysis is an interesting direction in machine learning. It mainly deals with data for which only the relationships `$<$', `$=$', `$>$' between pairs of points are known. We do an attempt of formalizing structures behind…

Fueled by deep learning, computer-aided diagnosis achieves huge advances. However, out of controlled lab environments, algorithms could face multiple challenges. Open set recognition (OSR), as an important one, states that categories unseen…

Large Language Models (LLMs) are increasingly used in Spoken Language Understanding (SLU), where effective multimodal learning depends on the alignment between audio and text. Despite various fusion methods, no standard metric exists to…

In this work, we introduce the concept of Active Representation Learning, a novel class of problems that intertwines exploration and representation learning within partially observable environments. We extend ideas from Active Simultaneous…

We investigate some types of composition operators, linear and not, and conditions for some spaces to be mapped into themselves and for the operators to satisfy some good properties.

We address the problem of unsupervised semantic segmentation of outdoor LiDAR point clouds in diverse traffic scenarios. The key idea is to leverage the spatiotemporal nature of a dynamic point cloud sequence and introduce drastically…

Discovering and exploring the underlying structure of multi-instrumental music using learning-based approaches remains an open problem. We extend the recent MusicVAE model to represent multitrack polyphonic measures as vectors in a latent…

While the successes of transformers across many domains are indisputable, accurate understanding of the learning mechanics is still largely lacking. Their capabilities have been probed on benchmarks which include a variety of structured and…

High-dimensional latent representations learned by neural network classifiers are notoriously hard to interpret. Especially in medical applications, model developers and domain experts desire a better understanding of how these latent…

Recent mainstream weakly-supervised semantic segmentation (WSSS) approaches mainly relies on image-level classification learning, which has limited representation capacity. In this paper, we propose a novel semantic learning based…

An experienced human Observer reading a document -- such as a crime report -- creates a succinct plot-like $\textit{``Working Memory''}$ comprising different actors, their prototypical roles and states at any point, their evolution over…

While deep reinforcement learning techniques have recently produced considerable achievements on many decision-making problems, their use in robotics has largely been limited to simulated worlds or restricted motions, since unconstrained…

Goal-conditioned planning benefits from learned low-dimensional representations of rich observations. While compact latent representations typically learned from variational autoencoders or inverse dynamics enable goal-conditioned decision…

Building deep reinforcement learning agents that can generalize and adapt to unseen environments remains a fundamental challenge for AI. This paper describes progresses on this challenge in the context of man-made environments, which are…

Data-driven approaches to assist operating room (OR) workflow analysis depend on large curated datasets that are time consuming and expensive to collect. On the other hand, we see a recent paradigm shift from supervised learning to…

The process of learning a manipulation task depends strongly on the action space used for exploration: posed in the incorrect action space, solving a task with reinforcement learning can be drastically inefficient. Additionally, similar…

Designing agent that can autonomously discover and learn a diversity of structures and skills in unknown changing environments is key for lifelong machine learning. A central challenge is how to learn incrementally representations in order…

Spatiotemporal modeling is critical for understanding complex systems across various scientific and engineering disciplines, but governing equations are often not fully known or computationally intractable due to inherent system complexity.…