Mobile robots are increasingly required to navigate and interact within unknown and unstructured environments to meet human demands. Demand-driven navigation (DDN) enables robots to identify and locate objects based on implicit human intent, even when object locations are unknown. However, traditional data-driven DDN methods rely on pre-collected data for model training and decision-making, limiting their generalization capability in unseen scenarios. In this paper, we propose CogDDN, a VLM-based framework that emulates the human cognitive and learning mechanisms by integrating fast and slow thinking systems and selectively identifying key objects essential to fulfilling user demands. CogDDN identifies appropriate target objects by semantically aligning detected objects with the given instructions. Furthermore, it incorporates a dual-process decision-making module, comprising a Heuristic Process for rapid, efficient decisions and an Analytic Process that analyzes past errors, accumulates them in a knowledge base, and continuously improves performance. Chain of Thought (CoT) reasoning strengthens the decision-making process. Extensive closed-loop evaluations on the AI2Thor simulator with the ProcThor dataset show that CogDDN outperforms single-view camera-only methods by 15\%, demonstrating significant improvements in navigation accuracy and adaptability. The project page is available at https://yuehaohuang.github.io/CogDDN/.

Combining these two properties, we introduce the reward-free deployment efficiency setting, a new paradigm for RL research.

In this work, we introduce WinoGA ViL: an online game of vision-and-language associations (e.g., between werewolves and a full moon), used as a dynamic evaluation benchmark.

We thank the reviewers for their detailed comments and their useful suggestions. In this rebuttal, we report results on larger transformer models. We study the less understood issues related to how well TLMs are able to perform long chains of reasoning. This directly motivates us to investigate if language models can also learn certain reasoning strategies. We will add this discussion to the paper.

We thank the reviewers for their helpful reviews. Please see the details below. See the figure below for the results of Reg. We now provide preliminary results for experiments on the DARTS search space. See the figure below (top right).

World models learn the consequences of actions in vision-based interactive systems. However, in practical scenarios such as autonomous driving, there commonly exists noncontrollable dynamics independent of the action signals, making it difficult to learn effective world models.

We observed that the latent representations correlate with the class assignment. Further, GPN is capable to separate nodes with perturbed features in the latent space.

Traditionally, BO assumes that the search space is known. However, in many problems, this assumption does not hold.