AwareVLN introduces a structural reasoning module and automatic data engine with progress division to equip VLN agents with self-awareness of agent state and task progress, outperforming prior methods on Habitat datasets.
Canonical reference
arXiv preprint arXiv:2506.09839 , year=
Canonical reference. 100% of citing Pith papers cite this work as background.
10
Pith papers citing it
Background
100% of classified citations
citation-role summary
background 5
citation-polarity summary
roles
background 5polarities
background 5representative citing papers
OmniNavBench is a unified benchmark for general-purpose navigation featuring composite multi-skill instructions, support for humanoid, quadrupedal and wheeled robots, and 1779 human teleoperated trajectories across 170 environments.
Distillation from frontier VLMs plus E-RLVR regularization produces a 4B local model that achieves 34.5% SR on OVON while cutting inference latency by 82.8%.
IDEA is a TTA framework for VLN that builds a dynamic asset library from Fisher-weighted soft prompts and domain coordinates, then uses convex-hull projection for cross-domain bridging and training-free adaptation.
FineCog-Nav uses fine-grained cognitive modules driven by foundation models to outperform zero-shot baselines in UAV navigation and introduces the AerialVLN-Fine benchmark with refined instructions.
HiRO-Nav adaptively triggers reasoning only on high-entropy actions via a hybrid training pipeline and shows better success-token trade-offs than always-reason or never-reason baselines on the CHORES-S benchmark.
ImagineNav++ achieves SOTA mapless visual navigation by prompting VLMs to select imagined future views generated from a human-preference-distilled module and maintained via selective foveation memory.
GN0 curates GN-Matrix dataset, builds 3DGS simulator and GN-Bench, and trains BAE model via supervised learning plus DAgger and RL to unify VLN tasks and outperform prior methods on GN-Bench and VLN-CE.
A survey of UAV vision-and-language navigation that establishes a methodological taxonomy, reviews resources and challenges, and proposes a forward-looking research roadmap.
The paper reviews conceptual foundations, methodological innovations, effective designs, critical challenges, and future directions for LLM-based Agentic Reinforcement Learning.
citing papers explorer
-
HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation
HiRO-Nav adaptively triggers reasoning only on high-entropy actions via a hybrid training pipeline and shows better success-token trade-offs than always-reason or never-reason baselines on the CHORES-S benchmark.
-
Rethinking Agentic Reinforcement Learning In Large Language Models
The paper reviews conceptual foundations, methodological innovations, effective designs, critical challenges, and future directions for LLM-based Agentic Reinforcement Learning.