Related papers: In-Context Credit Assignment via the Core
Settings such as lending and policing can be modeled by a centralized agent allocating a resource (loans or police officers) amongst several groups, in order to maximize some objective (loans given that are repaid or criminals that are…
Contextual bandits are widely used in industrial personalization systems. These online learning frameworks learn a treatment assignment policy in the presence of treatment effects that vary with the observed contextual features of the…
We address the problem of learning to assign prediction tasks to one agent from a set of available human or AI agents. In particular, we focus on the sequential learning of agent expertise and assignment policies where each agent is…
Budget allocation in online advertising deals with distributing the campaign (insertion order) level budgets to different sub-campaigns which employ different targeting criteria and may perform differently in terms of return-on-investment…
During complex knowledge work, people engage in iterative sensemaking: interpreting information, connecting ideas, and refining their understanding. Yet in current human-AI collaboration, these cognitive processes are difficult to share and…
We investigate whether and why people might adjust compensation for workers who use AI tools. Across 13 studies (N = 4,956), participants consistently lowered compensation for workers who used AI compared to those who did not. This "AI…
The ability to transfer knowledge to novel environments and tasks is a sensible desiderata for general learning agents. Despite the apparent promises, transfer in RL is still an open and little exploited research area. In this paper, we…
Video-based world models have recently garnered increasing attention for their ability to synthesize diverse and dynamic visual environments. In this paper, we focus on shared world modeling, where a model generates multiple videos from a…
While large text-to-image models are able to synthesize "novel" images, these images are necessarily a reflection of the training data. The problem of data attribution in such models -- which of the images in the training set are most…
Recent advances in text-to-image personalization have enabled high-quality and controllable image synthesis for user-provided concepts. However, existing methods still struggle to balance identity preservation with text alignment. Our…
The development of Multimodal Virtual Agents has made significant progress through the integration of Multimodal Large Language Models. However, mainstream training paradigms face key challenges: Behavior Cloning is simple and effective…
Context matters! Nevertheless, there has not been much research in exploiting contextual information in deep neural networks. For most part, the entire usage of contextual information has been limited to recurrent neural networks. Attention…
We consider the problem of repeatedly allocating multiple shareable public goods that have limited availability in an online setting without the use of money. In our setting, agents have additive values, and the value each agent receives…
Animal brains evolved to optimize behavior in dynamically changing environments, selecting actions that maximize future rewards. A large body of experimental work indicates that such optimization changes the wiring of neural circuits,…
Defining fairness in AI remains a persistent challenge, largely due to its deeply context-dependent nature and the lack of a universal definition. While numerous mathematical formulations of fairness exist, they sometimes conflict with one…
Generative AI is quickly becoming an integral part of people's everyday workflows. Early evidence has shown that while generative AI can increase individual-level productivity, it does so at the cost of collective diversity, potentially…
We propose a novel LLM-based framework for reasoning in discrete, game-theoretic tasks, illustrated with \emph{Tic-Tac-Toe}. The method integrates in-context learning with entropy-guided chain-of-thought (CoT) reasoning and adaptive context…
To make reinforcement learning more sample efficient, we need better credit assignment methods that measure an action's influence on future rewards. Building upon Hindsight Credit Assignment (HCA), we introduce Counterfactual Contribution…
New systems employ Machine Learning to sift through large knowledge sources, creating flexible Large Language Models. These models discern context and predict sequential information in various communication forms. Generative AI, leveraging…
We consider the problem of designing incentive-compatible, ex-post individually rational (IR) mechanisms for covering problems in the Bayesian setting, where players' types are drawn from an underlying distribution and may be correlated,…