Related papers: Dejavu: Towards Experience Feedback Learning for E…
The realization of Artificial General Intelligence (AGI) necessitates Embodied AI agents capable of robust spatial perception, effective task planning, and adaptive execution in physical environments. However, current large language models…
Vision-language models (VLMs) have shown remarkable general capabilities, yet embodied agents built on them fail at complex tasks, often skipping critical steps, proposing invalid actions, and repeating mistakes. These failures arise from a…
Current approaches to embodied AI tend to learn policies from expert demonstrations. However, without a mechanism to evaluate the quality of demonstrated actions, they are limited to learning from optimal behaviour, or they risk replicating…
Vision-Language-Action (VLA) models have demonstrated significant potential in the field of embodied intelligence, enabling agents to follow human instructions to complete complex tasks in physical environments. Existing embodied agents are…
Embodied navigation agents powered by large language models have shown strong performance on individual tasks but struggle to continually acquire new navigation skills, which suffer from catastrophic forgetting. We formalize this challenge…
Vision-language models (VLMs) have shown strong perception and reasoning abilities for instruction-following embodied agents. However, despite these abilities and their generalization performance, they still face limitations in…
Achieving truly adaptive embodied intelligence requires agents that learn not just by imitating static demonstrations, but by continuously improving through environmental interaction, which is akin to how humans master skills through…
Embodied visual tracking is to follow a target object in dynamic 3D environments using an agent's egocentric vision. This is a vital and challenging skill for embodied agents. However, existing methods suffer from inefficient training and…
Recent advances in embodied AI highlight the potential of vision language models (VLMs) as agents capable of perception, reasoning, and interaction in complex environments. However, top-performing systems rely on large-scale models that are…
The deployment of vision-language models remains constrained by substantial computational requirements. We present \textbf{FrEVL}, a framework exploring whether frozen pretrained embeddings can support effective vision-language…
Data privacy is a central problem for embodied agents that can perceive the environment, communicate with humans, and act in the real world. While helping humans complete tasks, the agent may observe and process sensitive information of…
Embodied agents can benefit from skills that guide object search, action execution, and state changes across diverse environments. Since embodied environments vary across layouts, object states, and other execution factors, these skills…
In Vision-and-Language Navigation (VLN), an embodied agent needs to reach a target destination with the only guidance of a natural language instruction. To explore the environment and progress towards the target location, the agent must…
Embodied cognition argues that intelligence arises from sensorimotor interaction rather than passive observation. It raises an intriguing question: do modern vision-language models (VLMs), trained largely in a disembodied manner, exhibit…
Embodied intelligence is often studied through specialized models for individual tasks such as manipulation or navigation, resulting in fragmented capabilities and limited generalization across tasks, environments, and robot embodiments. In…
Vision-Language-Action (VLA) models have recently enabled embodied agents to perform increasingly complex tasks by jointly reasoning over visual, linguistic, and motor modalities. However, we find that the prevailing notion of…
Vision-Language-Action (VLA) models show promise in embodied reasoning, yet remain far from true generalists-they often require task-specific fine-tuning, incur high compute costs, and generalize poorly to unseen tasks. We propose MetaVLA,…
Embodied agents are expected to operate persistently in dynamic physical environments, continuously acquiring new capabilities over time. Existing approaches to improving agent performance often rely on modifying the agent itself -- through…
Embodied task planning requires agents to execute long-horizon, goal-directed actions in complex 3D environments, where success depends on both immediate perception and accumulated experience across tasks. However, most existing LLM-based…
Visual foresight gives an agent a window into the future, which it can use to anticipate events before they happen and plan strategic behavior. Although impressive results have been achieved on video prediction in constrained settings,…