Related papers: Direct Evidence Delay with A Task Decreases Workin…

It has been suggested that direct reciprocity operates well within small groups of people where it would be hard to get away with cheating one another but no research has been done yet to show how exactly the mechanism of direct reciprocity…

Planning is useful. It lets people take actions that have desirable long-term consequences. But, planning is hard. It requires thinking about consequences, which consumes limited computational and cognitive resources. Thus, people should…

While large language models are able to retain vast amounts of world knowledge seen during pretraining, such knowledge is prone to going out of date and is nontrivial to update. Furthermore, these models are often used under temporal…

Stimulated by recent experimental results, we simulate ``temperature''-cycling experiments in a model for the compaction of granular media. We report on the existence of two types of memory effects: short-term dependence on the history of…

Quantifying the workplace productivity effects of Generative Artificial Intelligence is now central to economics, management, and public policy. The deployment of AI tools in customer service, writing, software development, and consulting…

Post-cutoff performance decay of LLMs has been widely interpreted as a temporal signal for benchmark contamination, where public information released before the training cutoff may have been included into training corpora and inflated model…

Memory can be defined as the ability to retain and recall information in a diverse range of forms. It is a vital component of the way in which we as human beings operate on a day to day basis. Given a particular situation, decisions are…

Reasoning models improve their problem-solving ability through inference-time scaling, allocating more compute via longer token budgets. Identifying which reasoning traces are likely to succeed remains a key opportunity: reliably predicting…

Several experimental studies claim to be able to predict the outcome of simple decisions from brain signals measured before subjects are aware of their decision. Often, these studies use multivariate pattern recognition methods with the…

Replaying past experiences has proven to be a highly effective approach for averting catastrophic forgetting in supervised continual learning. However, some crucial factors are still largely ignored, making it vulnerable to serious failure,…

Deep networks allow to obtain outstanding results in semantic segmentation, however they need to be trained in a single shot with a large amount of data. Continual learning settings where new classes are learned in incremental steps and…

Deep Reinforcement Learning is a promising tool for robotic control, yet practical application is often hindered by the difficulty of designing effective reward functions. Real-world tasks typically require optimizing multiple objectives…

Active learning has shown to reduce the number of experiments needed to obtain high-confidence drug-target predictions. However, in order to actually save experiments using active learning, it is crucial to have a method to evaluate the…

Chain-of-thought (CoT) prompting has become a widely used strategy for improving large language and multimodal model performance. However, it is still an open question under which settings CoT systematically reduces performance. In this…

We examine the effects of memory and different updating paradigms in a game-theoretic model of competitive learning, where agents are influenced in their choice of strategy by both the choices made by, and the consequent success rates of,…

For several years, the completion time and decoding delay problems in Instantly Decodable Network Coding (IDNC) were considered separately and were thought to completely act against each other. Recently, some works aimed to balance the…

Pre-trained language models demonstrate general intelligence and common sense, but long inputs quickly become a bottleneck for memorizing information at inference time. We resurface a simple method, Memorizing Transformers (Wu et al.,…

We propose that learning in deep neural networks proceeds in two phases: a rapid curve fitting phase followed by a slower compression or coarse graining phase. This view is supported by the shared temporal structure of three phenomena:…

Humans achieve efficient learning by relying on prior knowledge about the structure of naturally occurring tasks. There is considerable interest in designing reinforcement learning (RL) algorithms with similar properties. This includes…

Recently, small models with latent recursion have obtained promising results on complex reasoning tasks. These results are typically explained by the theory that such recursion increases a networks depth, allowing it to compactly emulate…