Tag
WEDGE 是一个弱点引导的导航学习框架，利用 LLM 从预训练策略的成功与失败轨迹中诊断失败模式，并据此生成针对性训练环境，在 ProcTHOR 和 HM3D 上显著优于随机与难例挖掘基线。
The paper introduces NavHarness, a training-free embodied navigation harness that integrates memory processing into the navigation loop, enabling agents to carry experience across sessions for lifelong navigation. On GOAT-Bench, it improves success rate by up to 22.6 points over context-only sessions and achieves state-of-the-art results with GPT-6/Astra.
HarnessVLN is a zero-shot, training-free framework for embodied navigation that unifies perception, retrieval, grounding, navigation, recovery, and termination through a unified tool interface, achieving state-of-the-art results on benchmarks like R2R and RxR.
LightNav-0 is a compact generalist navigation model that leverages pretrained vision-language models' spatial intelligence to achieve state-of-the-art embodied navigation across diverse tasks and robot embodiments.
TAMP-Nav is a unified framework that enhances embodied navigation by aligning vision-language models with 2D visual prompting, selective reasoning with compressed memory, and policy optimization, achieving state-of-the-art performance with high runtime and sample efficiency.
Image2Sim is a neural simulation framework that creates high-fidelity interactive environments from RGB-D images, enabling scalable training for embodied navigation agents. It generates nearly 20K scenes and over 10 million training samples, showing strong benchmark improvements and effective real-world zero-shot transfer.
PlatonicNav introduces a training-free framework for embodied navigation that uses vision-only semantic maps and blind matching to ground language goals, achieving generalization across tasks and embodiments without explicit cross-modal training.
AtlasVA is a teacher-free visual skill memory framework for vision-language model agents that uses spatial heatmaps, visual exemplars, and symbolic text skills to improve spatial decision-making in long-horizon tasks, outperforming baselines on several benchmarks.