Related papers: Attention Capture
A visual hard attention model actively selects and observes a sequence of subregions in an image to make a prediction. The majority of hard attention models determine the attention-worthy regions by first analyzing a complete image.…
Covert planning refers to a class of constrained planning problems where an agent aims to accomplish a task with minimal information leaked to a passive observer to avoid detection. However, existing methods of covert planning often…
Deep spatiotemporal models are used in a variety of computer vision tasks, such as action recognition and video object segmentation. Currently, there is a limited understanding of what information is captured by these models in their…
We explore a nuance to 'no arbitrage' in relation to 'information efficiency': acting immediately on an arbitrage is sometimes suboptimal; in such cases optimised trading can suppress the anticipation of predictable risk-outcomes, thereby…
We introduce the Momentum Transformer, an attention-based deep-learning architecture, which outperforms benchmark time-series momentum and mean-reversion trading strategies. Unlike state-of-the-art Long Short-Term Memory (LSTM)…
Attention endows animals an ability to concentrate on the most relevant information among a deluge of distractors at any given time, either through volitionally 'top-down' biasing, or driven by automatically 'bottom-up' saliency of stimuli,…
Most decisions require information gathering from a stimulus presented with different gaps. Indeed, the brain process of this integration is rarely ambiguous. Recently, it has been claimed that humans can optimally integrate the information…
Most research on within-day dynamic traffic equilibrium with information provision implicitly considers travel time information, often assuming information to be perfect or imperfect based on travelers' perception error. However, lacking…
Vision transformers using self-attention or its proposed alternatives have demonstrated promising results in many image related tasks. However, the underpinning inductive bias of attention is not well understood. To address this issue, this…
We study the impact of learning on the optimal policy and the time-to-decision in an infinite-horizon Bayesian sequential decision model with two irreversible alternatives, exit and expansion. In our model, a firm undertakes a small-scale…
The minimization of the length of syntactic dependencies is a well-established principle of word order and the basis of a mathematical theory of word order. Here we complete that theory from the perspective of information theory, adding a…
Human cognition is punctuated by abrupt, spontaneous shifts between topics-driven by emotional, contextual, or associative cues-a phenomenon known as spontaneous thought in neuroscience. In contrast, self-attention based models depend on…
Decomposing knowledge into interchangeable pieces promises a generalization advantage when there are changes in distribution. A learning agent interacting with its environment is likely to be faced with situations requiring novel…
In the persuasion model, apart from a few special cases, comparative statics has been an open question. We answer it, delineating which shifts of the sender's interim payoff lead her optimally to choose a more informative signal. Our first…
This paper studies the persuasion of a receiver who accesses information only if she exerts costly attention effort. A sender designs an experiment to persuade the receiver to take a specific action. The experiment affects the receiver's…
This paper focuses on the use of knowledge possessed by designers. Data collection was based on observations (by the cognitive ergonomics researcher) and simultaneous verbalisations (by the designers) in empirical studies conducted in the…
In POMDPs, information about the hidden state, delivered through observations, is both valuable to the agent, allowing it to base its actions on better informed internal states, and a "curse", exploding the size and diversity of the…
Task-agnostic prompt compression leverages the redundancy in natural language to reduce computational overhead and enhance information density within prompts, especially in long-context scenarios. Existing methods predominantly rely on…
This paper analyzes a dynamic interaction between a fully rational, privately informed sender and a boundedly rational, uninformed receiver with memory constraints. The sender controls the flow of information, while the receiver designs a…
We study the evolution of information in interactive decision making through the lens of a stochastic multi-armed bandit problem. Focusing on a fundamental example where a unique optimal arm outperforms the rest by a fixed margin, we…