Related papers: Representational Tenets for Memory Athletics
Anyone who has tried to memorize a one-hundred-digit number can attest that the human brain acquires abstract information slowly. However, following a three-decade increase of results at memory competitions, the best competitors manage to…
A deep understanding of sports, a field rich in strategic and dynamic content, is crucial for advancing Natural Language Processing (NLP). This holds particular significance in the context of evaluating and advancing Large Language Models…
In Partially Observable Markov Decision Processes, integrating an agent's history into memory poses a significant challenge for decision-making. Traditional imitation learning, relying on observation-action pairs for expert demonstrations,…
Modern deep-learning training is not memoryless. Updates depend on optimizer moments and averaging, data-order policies (random reshuffling vs with-replacement, staged augmentations and replay), the nonconvex path, and auxiliary state…
Understanding how individuals perceive and recall information in their natural environments is critical to understanding potential failures in perception (e.g., sensory loss) and memory (e.g., dementia). Event segmentation, the process of…
Memory is critical for LLM-based agents to preserve past observations for future decision-making, where factual memory serves as its foundational part. However, existing approaches to constructing factual memory face several limitations.…
We present a reproduction study of "Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals" (Ortu et al., 2024), which investigates competition of mechanisms in language models between factual recall and…
Verbatim memorization in Large Language Models (LLMs) is a multifaceted phenomenon involving distinct underlying mechanisms. We introduce a novel method to analyze the different forms of memorization described by the existing taxonomy.…
Estimating action quality, the process of assigning a "score" to the execution of an action, is crucial in areas such as sports and health care. Unlike action recognition, which has millions of examples to learn from, the action quality…
The mechanics of complex bodies with memory effects is discussed in linearized setting. The attention is focused on the characterization of free energies in terms of minimum work and maximum recoverable work in the bulk and along a…
Evaluating large language models (LLMs) on question answering often relies on static benchmarks that reward memorization and understate the role of retrieval, failing to capture the dynamic nature of world knowledge. We present…
The coding mechanism of sensory memory on the neuron scale is one of the most important questions in neuroscience. We have put forward a quantitative neural network model, which is self organized, self similar, and self adaptive, just like…
Neural attention models have achieved significant improvements on many natural language processing tasks. However, the quadratic memory complexity of the self-attention module with respect to the input length hinders their applications in…
In this paper we present the design and evaluation of an end-to-end trainable, deep neural network with a visual attention mechanism for memorability estimation in still images. We analyze the suitability of transfer learning of deep models…
Because the decathlon tests many facets of athleticism, including sprinting, throwing, jumping, and endurance, many consider it to be the ultimate test of athletic ability. On this view, estimating the maximal decathlon score and…
Spaced repetition is among the most studied learning strategies in the cognitive science literature. It consists in temporally distributing exposure to an information so as to improve long-term memorization. Providing students with an…
Stack-augmented recurrent neural networks (RNNs) have been of interest to the deep learning community for some time. However, the difficulty of training memory models remains a problem obstructing the widespread use of such models. In this…
Large language models (LLMs) regularly demonstrate new and impressive performance on a wide range of language, knowledge, and reasoning benchmarks. Such rapid progress has led many commentators to argue that LLM general cognitive…
We describe a new class of learning models called memory networks. Memory networks reason with inference components combined with a long-term memory component; they learn how to use these jointly. The long-term memory can be read and…
We explore a new class of brain encoding model by adding memory-related information as input. Memory is an essential brain mechanism that works alongside visual stimuli. During a vision-memory cognitive task, we found the non-visual brain…