Related papers: Event-Centric World Modeling with Memory-Augmented…

Semantic information in embodied AI is inherently multi-source and multi-stage, making it challenging to fully leverage for achieving stable perception-to-action loops in real-world environments. Early studies have combined manual…

Active recognition enables robots to intelligently explore novel observations, thereby acquiring more information while circumventing undesired viewing conditions. Recent approaches favor learning policies from simulated or collected data,…

Data-efficient learning remains a central challenge in autonomous driving due to the high cost and safety risks of large-scale real-world interaction. Although world-model-based reinforcement learning enables policy optimization through…

Learning to perform activities through demonstration requires extracting meaningful information about the environment from observations. In this research, we investigate the challenge of planning high-level goal-oriented actions in a…

Unlike popular modularized framework, end-to-end autonomous driving seeks to solve the perception, decision and control problems in an integrated way, which can be more adapting to new scenarios and easier to generalize at scale. However,…

Embodied agents operating in complex and uncertain environments face considerable challenges. While some advanced agents handle complex manipulation tasks with proficiency, their success often hinges on extensive training data to develop…

Driving in safety-critical scenarios requires quick, context-aware decision-making grounded in both situational understanding and experiential reasoning. Large Language Models (LLMs), with their powerful general-purpose reasoning…

Vision-Language-Action (VLA) models have achieved strong semantic generalization for embodied policy learning, yet they learn reactive observation-to-action mappings without explicitly modeling how the physical world evolves under…

Reinforcement learning suffers from limitations in real practices primarily due to the number of required interactions with virtual environments. It results in a challenging problem because we are implausible to obtain a local optimal…

Autonomous agent frameworks still struggle to reconcile long-term experiential learning with real-time, context-sensitive decision-making. In practice, this gap appears as static cognition, rigid workflow dependence, and inefficient context…

World models enable agents to plan within imagined environments by predicting future states conditioned on past observations and actions. However, their ability to plan over long horizons is limited by the effective memory span of the…

Human memory is inherently prone to forgetting. To address this, multimodal embedding models have been introduced, which transform diverse real-world data into a unified embedding space. These embeddings can be retrieved efficiently, aiding…

End-to-end autonomous driving aims to generate safe and plausible planning policies from raw sensor input. Driving world models have shown great potential in learning rich representations by predicting the future evolution of a driving…

Robust coordination is critical for effective decision-making in multi-agent systems, especially under partial observability. A central question in Multi-Agent Reinforcement Learning (MARL) is whether to engineer communication protocols or…

Event cameras asynchronously capture brightness changes with low latency, high temporal resolution, and high dynamic range. However, annotation of event data is a costly and laborious process, which limits the use of deep learning methods…

Object Goal Navigation-requiring an agent to locate a specific object in an unseen environment-remains a core challenge in embodied AI. Although recent progress in Vision-Language Model (VLM)-based agents has demonstrated promising…

Humans perceive and reason about their surroundings in four dimensions by building persistent, structured internal representations that encode semantic meaning, spatial layout, and temporal dynamics. These multimodal memories enable them to…

Autonomous driving systems depend on on models that can reason about high-level scene contexts and accurately predict the dynamics of their surrounding environment. Vision- Language Models (VLMs) have recently emerged as promising tools for…

Recent advancements in 3D reconstruction and neural rendering have enhanced the creation of high-quality digital assets, yet existing methods struggle to generalize across varying object shapes, textures, and occlusions. While Next Best…

Achieving human-like reasoning in deep learning models for complex tasks in unknown environments remains a critical challenge in embodied intelligence. While advanced vision-language models (VLMs) excel in static scene understanding, their…