Related papers: DMWM: Dual-Mind World Model with Long-Term Imagina…

Emerging networked systems such as industrial IoT and real-time cyber-physical infrastructures demand intelligent scheduling strategies capable of adapting to dynamic traffic, deadlines, and interference constraints. In this work, we…

Despite the popularity of reinforcement learning (RL) in wireless networks, existing approaches that rely on model-free RL (MFRL) and model-based RL (MBRL) are data inefficient and short-sighted. Such RL-based solutions cannot generalize to…

The medial temporal lobe (MTL), a brain region containing the hippocampus and nearby areas, is hypothesized to be an experience-construction system in mammals, supporting both recall and imagination of temporally-extended sequences of…

Vision-language models (VLMs) have shown strong performance on static visual understanding, yet they still struggle with dynamic spatial reasoning that requires imagining how scenes evolve under egocentric motion. Recent efforts address…

Deploying learned control policies in real-world environments poses a fundamental challenge. When system dynamics change unexpectedly, performance degrades until models are retrained on new data. We introduce Reflexive World Models (RWM), a…

Real-time human-artificial intelligence (AI) collaboration is crucial yet challenging, especially when AI agents must adapt to diverse and unseen human behaviors in dynamic scenarios. Existing large language model (LLM) agents often fail to…

World models are a fundamental component in model-based reinforcement learning (MBRL). To perform temporally extended and consistent simulations of the future in partially observable environments, world models need to possess long-term…

World models enable model-based planning through learned latent dynamics, but imagined rollouts become unstable as the planning horizon grows or the dynamics distribution shifts. We argue that this instability reflects two missing…

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…

Humans leverage rich internal models of the world to reason about the future, imagine counterfactuals, and adapt flexibly to new situations. In Reinforcement Learning (RL), world models aim to capture how the environment evolves in response…

Social robot navigation increasingly relies on large language models for reasoning, path planning, and enabling movement in dynamic human spaces. However, relying solely on LLMs for planning often leads to unpredictable and unsafe…

The remarkable recent advances in object-centric generative world models raise a few questions. First, while many of the recent achievements are indispensable for making a general and versatile world model, it is quite unclear how these…

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,…

Learning predictive world models from raw visual observations is a central challenge in reinforcement learning (RL), especially for robotics and continuous control. Conventional model-based RL frameworks directly condition future…

Language agents increasingly require persistent worlds in which they can act, remember, and learn. Existing approaches sit at two extremes: conventional web frameworks provide reliable but fixed contexts backed by databases, while fully…

Vision-language model (VLM) shows promise for high-level planning in smart manufacturing, yet their deployment in dynamic workcells faces two critical challenges: (1) stateless operation, they cannot persistently track out-of-view states,…

Training visual reinforcement learning agents in a high-dimensional open world presents significant challenges. While various model-based methods have improved sample efficiency by learning interactive world models, these agents tend to be…

Although Reinforcement Learning (RL) agents are effective in well-defined environments, they often struggle to generalize their learned policies to dynamic settings due to their reliance on trial-and-error interactions. Recent work has…

The computational role of imagination remains debated. While classical accounts emphasize reward maximization, emerging evidence suggests it accesses internal world models (IWMs). We employ psychological network analysis to compare IWMs in…

Cooperative multi-agent planning requires agents to make joint decisions with partial information and limited communication. Coordination at the trajectory level often fails, as small deviations in timing or movement cascade into conflicts.…