Related papers: Creating General User Models from Computer Use

Evaluating recommender systems remains challenging due to the gap between offline metrics and real user behavior, as well as the scarcity of interaction data. Recent work explores large language model (LLM) agents as synthetic users, yet…

Large language models (LLMs) have advanced the field of artificial intelligence (AI) and are a powerful enabler for interactive systems. However, they still face challenges in long-term interactions that require adaptation towards the user…

With the rapid expansion of user bases on short video platforms, personalized recommendation systems are playing an increasingly critical role in enhancing user experience and optimizing content distribution. Traditional interest modeling…

We introduce the GAMBIT Universal Model Machine (GUM), a tool for automatically generating code for the global fitting software framework GAMBIT, based on Lagrangian-level inputs. GUM accepts models written symbolically in FeynRules and…

Computer-use agents (CUAs) automate on-screen work, as illustrated by GPT-5.4 and Claude. Yet their reliability on complex, low-frequency interactions is still poor, limiting user trust. Our analysis of failure cases from advanced models…

Accurately predicting future behaviors of surrounding vehicles is an essential capability for autonomous vehicles in order to plan safe and feasible trajectories. The behaviors of others, however, are full of uncertainties. Both rational…

We consider the problem of predicting perturbation effects via causal models. In many applications, it is a priori unknown which mechanisms of a system are modified by an external perturbation, even though the features of the perturbation…

Generative Artificial Intelligence systems have been developed for image, code, story, and game generation with the goal of facilitating human creativity. Recent work on neural generative systems has emphasized one particular means of…

Generative models trained on internet data have revolutionized how text, image, and video content can be created. Perhaps the next milestone for generative models is to simulate realistic experience in response to actions taken by humans,…

The paper proposes an approach to modeling users of large Web sites based on combining different data sources: access logs and content of the accessed pages are combined with semantic information about the Web pages, the users and the…

Semantically connecting users and items is a fundamental problem for the matching stage of an industrial recommender system. Recent advances in this topic are based on multi-channel retrieval to efficiently measure users' interest on items…

The existing collaborative recommendation models that use multi-modal information emphasize the representation of users' preferences but easily ignore the representation of users' dislikes. Nevertheless, modelling users' dislikes…

In human-in-the-loop machine learning, the user provides information beyond that in the training data. Many algorithms and user interfaces have been designed to optimize and facilitate this human--machine interaction; however, fewer studies…

Large Language Models (LLMs) have emerged as personalized assistants for users across a wide range of tasks -- from offering writing support to delivering tailored recommendations or consultations. Over time, the interaction history between…

Simulating nuanced user experiences within complex interactive search systems poses distinct challenge for traditional methodologies, which often rely on static user proxies or, more recently, on standalone large language model (LLM) agents…

This paper introduces the concept of Language-Guided World Models (LWMs) -- probabilistic models that can simulate environments by reading texts. Agents equipped with these models provide humans with more extensive and efficient control,…

Emotions are an inherent part of human interactions, and consequently, it is imperative to develop AI systems that understand and recognize human emotions. During a conversation involving various people, a person's emotions are influenced…

Social activities result from complex joint activity-travel decisions between group members. While observing the decision-making process of these activities is difficult via traditional travel surveys, the advent of new types of data, such…

Unlike static and rigid user interfaces, generative and malleable user interfaces offer the potential to respond to diverse users' goals and tasks. However, current approaches primarily rely on generating code, making it difficult for…

We introduce UViM, a unified approach capable of modeling a wide range of computer vision tasks. In contrast to previous models, UViM has the same functional form for all tasks; it requires no task-specific modifications which require…