相关论文: A Biologically-Inspired Dual Stream World Model

This paper models information diffusion in a network of Large Language Models (LLMs) that is designed to answer queries from distributed datasets, where the LLMs can hallucinate the answer. We introduce a two-time-scale dynamical model for…

Understanding how humans process visual information is one of the crucial steps for unraveling the underlying mechanism of brain activity. Recently, this curiosity has motivated the fMRI-to-image reconstruction task; given the fMRI data…

Generative models such as diffusion models, excel at capturing high-dimensional distributions with diverse input modalities, e.g. robot trajectories, but are less effective at multi-step constraint reasoning. Task and Motion Planning (TAMP)…

Tool use in stateful environments presents unique challenges for large language models (LLMs), where existing test-time compute strategies relying on repeated trials in the environment are impractical. We propose dynamics modelling (DyMo),…

Induction head mechanism is a part of the computational circuits for in-context learning (ICL) that enable large language models (LLMs) to adapt to new tasks without fine-tuning. Most existing work explains the training dynamics behind…

Large Language Models (LLMs) can serve as world models to enhance agent decision-making in digital environments by simulating future states and predicting action outcomes, potentially eliminating costly trial-and-error exploration. However,…

The hippocampus is an essential brain region for spatial memory and learning. Recently, a theoretical model of the hippocampus based on temporal difference (TD) learning has been published. Inspired by the successor representation (SR)…

The ability to simulate the effects of future actions on the world is a crucial ability of intelligent embodied agents, enabling agents to anticipate the effects of their actions and make plans accordingly. While a large body of existing…

World Models serve as tools for understanding the current state of the world and predicting its future dynamics, with broad application potential across numerous fields. As a key component of world knowledge, emotion significantly…

Current research efforts are focused on enhancing the thinking and reasoning capability of large language model (LLM) by prompting, data-driven emergence and inference-time computation. In this study, we consider stimulating language…

Legged locomotion over various terrains is challenging and requires precise perception of the robot and its surroundings from both proprioception and vision. However, learning directly from high-dimensional visual input is often…

Building a human-like system that continuously interacts with complex environments -- whether simulated digital worlds or human society -- presents several key challenges. Central to this is enabling continuous, high-frequency interactions,…

World models are becoming central to robotic planning and control as they enable prediction of future state transitions. Existing approaches often emphasize video generation or natural-language prediction, which are difficult to ground in…

Liquid State Machine (LSM) is a neural model with real time computations which transforms the time varying inputs stream to a higher dimensional space. The concept of LSM is a novel field of research in biological inspired computation with…

This paper describes a framework for modeling the interface between perception and memory on the algorithmic level of analysis. It is consistent with phenomena associated with many different brain regions. These include view-dependence (and…

We introduce StorySim, a programmable framework for synthetically generating stories to evaluate the theory of mind (ToM) and world modeling (WM) capabilities of large language models (LLMs). Unlike prior benchmarks that may suffer from…

Brain-inspired spiking neural networks (SNNs) have garnered significant research attention in algorithm design and perception applications. However, their potential in the decision-making domain, particularly in model-based reinforcement…

Deep neural network (DNN) based machine perception frameworks process the entire input in a one-shot manner to provide answers to both "what object is being observed" and "where it is located". In contrast, the "two-stream hypothesis" from…

Deep learning models loosely mimic bottom-up signal pathways from low-order sensory areas to high-order cognitive areas. After training, DL models can outperform humans on some domain-specific tasks, but their decision-making process has…

Hippocampal reverse replay is thought to contribute to learning, and particularly reinforcement learning, in animals. We present a computational model of learning in the hippocampus that builds on a previous model of the…