Related papers: PAR: Political Actor Representation Learning with …

Social choice theory is the study of preference aggregation across a population, used both in mechanism design for human agents and in the democratic alignment of language models. In this study, we propose the representative social choice…

Imitation learning, which learns agent policy by mimicking expert demonstration, has shown promising results in many applications such as medical treatment regimes and self-driving vehicles. However, it remains a difficult task to interpret…

Existing pedestrian attribute recognition (PAR) algorithms are mainly developed based on a static image. However, the performance is not reliable for images with challenging factors, such as heavy occlusion, motion blur, etc. In this work,…

Understanding political polarization on social platforms is important as public opinions may become increasingly extreme when they are circulated in homogeneous communities, thus potentially causing damage in the real world. Automatically…

We introduce a novel approach to transformers that learns hierarchical representations in multiparty dialogue. First, three language modeling tasks are used to pre-train the transformers, token- and utterance-level language modeling and…

In this paper we extend some recent results on an operatorial approach to the description of alliances between political parties interacting among themselves and with a basin of electors. In particular, we propose and compare three…

This work addresses the problem of Social Activity Recognition (SAR), a critical component in real-world tasks like surveillance and assistive robotics. Unlike traditional event understanding approaches, SAR necessitates modeling individual…

Deliberative processes play a vital role in shaping opinions, decisions and policies in our society. In contrast to persuasive debates, deliberation aims to foster understanding of conflicting perspectives among interested parties. The…

Although neural models have achieved competitive results in dialogue systems, they have shown limited ability in representing core semantics, such as ignoring important entities. To this end, we exploit Abstract Meaning Representation (AMR)…

Training machine learning models with the only accuracy as a final goal may promote prejudices and discriminatory behaviors embedded in the data. One solution is to learn latent representations that fulfill specific fairness metrics.…

Pedestrian Attribute Recognition (PAR) is a challenging task in intelligent video surveillance. Two key challenges in PAR include complex alignment relations between images and attributes, and imbalanced data distribution. Existing…

We provide explicit, finite-sample guarantees for learning causal representations from data with a sublinear number of environments. Causal representation learning seeks to provide a rigourous foundation for the general representation…

We propose an approach to self-supervised representation learning based on maximizing mutual information between features extracted from multiple views of a shared context. For example, one could produce multiple views of a local…

Driving in a dynamic, multi-agent, and complex urban environment is a difficult task requiring a complex decision-making policy. The learning of such a policy requires a state representation that can encode the entire environment. Mid-level…

We explore the problem of learning to decompose spatial tasks into segments, as exemplified by the problem of a painting robot covering a large object. Inspired by the ability of classical decision tree algorithms to construct structured…

Despite the great success of face recognition techniques, recognizing persons under unconstrained settings remains challenging. Issues like profile views, unfavorable lighting, and occlusions can cause substantial difficulties. Previous…

In this work we propose a simple and efficient framework for learning sentence representations from unlabelled data. Drawing inspiration from the distributional hypothesis and recent work on learning sentence representations, we reformulate…

We address the problem of learning representations from observations of a scene involving an agent and an external object the agent interacts with. To this end, we propose a representation learning framework extracting the location in…

The legal domain is a vast and complex field that involves a considerable amount of text analysis, including laws, legal arguments, and legal opinions. Legal practitioners must analyze these texts to understand legal cases, research legal…

Large language models offer opportunities to simulate multi-party deliberation, but realistic modeling remains limited by a lack of speaker-attributed data. Transcripts produced via automatic speech recognition (ASR) assign anonymous…