USS is an end-to-end framework for embodied visual tracking that fuses text, point, box, and mask prompts via modality-specific encoders and hybrid attention, augmented by a latent world model, and demonstrates higher success rates with spatial cues on real robots and competitive simulation performa
hub Canonical reference
Embodied navigation foundation model
Canonical reference. 88% of citing Pith papers cite this work as background.
28
Pith papers citing it
Background
88% of classified citations
hub tools
citation-role summary
background 7
baseline 1
citation-polarity summary
years
2026 28representative citing papers
The paper introduces a Trajectory Waypoint paradigm with a TSDF-guided diffusion policy and trajectory-enhanced navigator that achieves better performance on VLN-CE benchmarks by ensuring waypoint reachability and planning-execution consistency.
POINav-Bench provides the first high-fidelity real-world benchmark for POI-goal VLN using 3DGS reconstructions of 126k m² with 163 POIs, supported by a Brain-Action framework and 70K real signage-entrance dataset.
Formalizes video world models as group actions on states and uses latent regularization with synthesized supervision to enforce consistency, introducing GAC and GAR metrics that improve structural correctness in SOTA models.
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.
Fine-tuning multimodal models on a new synthetic spatial benchmark improves generative spatial compliance on real and synthetic tasks and transfers to better spatial understanding.
QuadAgent uses an asynchronous multi-agent architecture with an Impression Graph for scene memory and vision-based avoidance to enable training-free vision-language guided agile quadrotor flight, outperforming baselines in simulations and achieving real-world speeds up to 5 m/s.
NeuroKalman mitigates state drift in vision-language UAV navigation by using memory-augmented Kalman filtering where attention retrieves historical anchors to correct predictions without gradient updates.
A feed-forward feature-Gaussian plus one-step geometry-aware pixel-flow simulator converts large image collections into 20K interactive scenes and 10M+ navigation samples that improve zero-shot Habitat and real-robot performance.
A frozen MLLM with LoRA-on-language and a discrete token waypoint interface navigates four unseen real-world environments after just 8.7 hours of training data.
DynFly bridges high-level UAV navigation reasoning to continuous motion via B-spline trajectory generation with flow matching and UAV-specific dynamic supervision, yielding metric gains on the OpenUAV benchmark.
SAGE-Nav decouples LLM global planning from reactive control via hierarchical scene graphs and alignment fusion, reporting SOTA results on i-THOR and RoboTHOR with improved efficiency and zero-shot generalization.
Vesta is a unified embodied generalist model that outperforms specialist baselines by over 20% on average and improves real-world robotic task success by over 35%.
GroundControl estimates navigation uncertainty via statistical deviation from nominal goal-directed distance dynamics, achieving low E-AURC (0.0024 weighted for GPT-4o) on EB-Navigation splits and outperforming entropy and conformal baselines under SRCN evaluation.
Goal2Pixel grounds VLN-CE goals to image pixels via VLM prediction plus keyframe memory, reaching 54.1% SR on R2R-CE Val-Unseen with 7.75 calls per episode versus 46.62 for action prediction.
A zero-shot unified agent for VLN-CE, ObjectNav, EQA and Aerial-VLN on wheeled, quadruped, humanoid and UAV platforms that translates language and vision inputs into actions via MLLMs plus TDM and SCB mechanisms, matching trained foundation models on multiple benchmarks.
GA-VLN builds a geometry-aware BEV representation from RGB-D inputs plus 3D foundation model features to deliver state-of-the-art vision-language navigation using only navigation data.
SpaAct activates spatial awareness in VLMs using action retrospection, future frame prediction, and progressive curriculum learning to reach SOTA on VLN-CE benchmarks.
Privatar partitions VR avatar reconstruction via frequency-domain decomposition, keeping sensitive components local and offloading the rest with distribution-aware minimal perturbation noise, achieving 2.37x throughput with provable privacy.
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.
MVP-Nav reconstructs explicit 3D physical occupancy from monocular RGB using foundation models and integrates it with semantic priorities via a Multi-layer Value Map for grounded planning in zero-shot object navigation.
G-DRAGON framework maps language commands to OSM coordinates via lightweight LLM for global planning and uses frontier exploration for local targets, outperforming baselines in simulation and completing real UGV person-search missions up to 500m.
Robo-Cortex proposes a self-evolving embodied navigation agent using dual-grain cognitive memory and autonomous knowledge induction from trajectories, reporting SPL gains on IGNav, AR, AEQA and preliminary real-robot tests.
StereoNav reaches new benchmark highs on R2R-CE and RxR-CE and improves real-robot reliability by supplying persistent target-location priors and stereo-derived geometry that stay stable under lighting changes and blur.
citing papers explorer
-
USS: Unified Spatial-Semantic Prompts for Embodied Visual Tracking with Latent Dynamics Learning
USS is an end-to-end framework for embodied visual tracking that fuses text, point, box, and mask prompts via modality-specific encoders and hybrid attention, augmented by a latent world model, and demonstrates higher success rates with spatial cues on real robots and competitive simulation performa
-
Beyond Waypoints: A Trajectory-Centric Waypointing Paradigm for Vision-Language Navigation
The paper introduces a Trajectory Waypoint paradigm with a TSDF-guided diffusion policy and trajectory-enhanced navigator that achieves better performance on VLN-CE benchmarks by ensuring waypoint reachability and planning-execution consistency.
-
POINav: Benchmarking and Enhancing Final-Meters Arrival in Real-World Vision-Language Navigation
POINav-Bench provides the first high-fidelity real-world benchmark for POI-goal VLN using 3DGS reconstructions of 126k m² with 163 POIs, supported by a Brain-Action framework and 70K real signage-entrance dataset.
-
World Models as Group Actions
Formalizes video world models as group actions on states and uses latent regularization with synthesized supervision to enforce consistency, introducing GAC and GAR metrics that improve structural correctness in SOTA models.
-
Beyond Isolation: A Unified Benchmark for General-Purpose Navigation
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.
-
Exploring Spatial Intelligence from a Generative Perspective
Fine-tuning multimodal models on a new synthetic spatial benchmark improves generative spatial compliance on real and synthetic tasks and transfers to better spatial understanding.
-
QuadAgent: A Responsive Agent System for Vision-Language Guided Quadrotor Agile Flight
QuadAgent uses an asynchronous multi-agent architecture with an Impression Graph for scene memory and vision-based avoidance to enable training-free vision-language guided agile quadrotor flight, outperforming baselines in simulations and achieving real-world speeds up to 5 m/s.
-
Mitigating Error Accumulation in Continuous Navigation via Memory-Augmented Kalman Filtering
NeuroKalman mitigates state drift in vision-language UAV navigation by using memory-augmented Kalman filtering where attention retrieves historical anchors to correct predictions without gradient updates.
-
Image2Sim: Scaling Embodied Navigation via Generative Neural Simulator
A feed-forward feature-Gaussian plus one-step geometry-aware pixel-flow simulator converts large image collections into 20K interactive scenes and 10M+ navigation samples that improve zero-shot Habitat and real-robot performance.
-
GemNav: Discrete-Token Visual Robot Navigation using a Multimodal Large Language Model
A frozen MLLM with LoRA-on-language and a discrete token waypoint interface navigates four unseen real-world environments after just 8.7 hours of training data.
-
DynFly: Dynamic-Aware Continuous Trajectory Generation for UAV Vision-Language Navigation in Urban Environments
DynFly bridges high-level UAV navigation reasoning to continuous motion via B-spline trajectory generation with flow matching and UAV-specific dynamic supervision, yielding metric gains on the OpenUAV benchmark.
-
SAGE-Nav: Leveraging LLM Planning and Alignment Fusion for Hierarchical Scene Graph-Guided Navigation
SAGE-Nav decouples LLM global planning from reactive control via hierarchical scene graphs and alignment fusion, reporting SOTA results on i-THOR and RoboTHOR with improved efficiency and zero-shot generalization.
-
Vesta: A Generalist Embodied Reasoning Model
Vesta is a unified embodied generalist model that outperforms specialist baselines by over 20% on average and improves real-world robotic task success by over 35%.
-
GroundControl: Anticipating Navigation Failures in Vision-Language Agents via Trajectory-Consistent Uncertainty Estimates
GroundControl estimates navigation uncertainty via statistical deviation from nominal goal-directed distance dynamics, achieving low E-AURC (0.0024 weighted for GPT-4o) on EB-Navigation splits and outperforming entropy and conformal baselines under SRCN evaluation.
-
Goal2Pixel: Grounding Goals to Pixels for Vision-Language Navigation
Goal2Pixel grounds VLN-CE goals to image pixels via VLM prediction plus keyframe memory, reaching 54.1% SR on R2R-CE Val-Unseen with 7.75 calls per episode versus 46.62 for action prediction.
-
Uni-LaViRA: Language-Vision-Robot Actions Translation for Unified Embodied Navigation
A zero-shot unified agent for VLN-CE, ObjectNav, EQA and Aerial-VLN on wheeled, quadruped, humanoid and UAV platforms that translates language and vision inputs into actions via MLLMs plus TDM and SCB mechanisms, matching trained foundation models on multiple benchmarks.
-
GA-VLN: Geometry-Aware BEV Representation for Efficient Vision-Language Navigation
GA-VLN builds a geometry-aware BEV representation from RGB-D inputs plus 3D foundation model features to deliver state-of-the-art vision-language navigation using only navigation data.
-
SpaAct: Spatially-Activated Transition Learning with Curriculum Adaptation for Vision-Language Navigation
SpaAct activates spatial awareness in VLMs using action retrospection, future frame prediction, and progressive curriculum learning to reach SOTA on VLN-CE benchmarks.
-
Dual-Anchoring: Addressing State Drift in Vision-Language Navigation
Privatar partitions VR avatar reconstruction via frequency-domain decomposition, keeping sensitive components local and offloading the rest with distribution-aware minimal perturbation noise, achieving 2.37x throughput with provable privacy.
-
FineCog-Nav: Integrating Fine-grained Cognitive Modules for Zero-shot Multimodal UAV Navigation
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.
-
MVP-Nav: Multi-layer Value Map Planner Navigator
MVP-Nav reconstructs explicit 3D physical occupancy from monocular RGB using foundation models and integrates it with semantic priorities via a Multi-layer Value Map for grounded planning in zero-shot object navigation.
-
G-DRAGON: Geospatial Reasoning and Dynamic Planning for Retrieval-Augmented Outdoor Navigation
G-DRAGON framework maps language commands to OSM coordinates via lightweight LLM for global planning and uses frontier exploration for local targets, outperforming baselines in simulation and completing real UGV person-search missions up to 500m.
-
Robo-Cortex: A Self-Evolving Embodied Agent via Dual-Grain Cognitive Memory and Autonomous Knowledge Induction
Robo-Cortex proposes a self-evolving embodied navigation agent using dual-grain cognitive memory and autonomous knowledge induction from trajectories, reporting SPL gains on IGNav, AR, AEQA and preliminary real-robot tests.
-
What Limits Vision-and-Language Navigation ?
StereoNav reaches new benchmark highs on R2R-CE and RxR-CE and improves real-robot reliability by supplying persistent target-location priors and stereo-derived geometry that stay stable under lighting changes and blur.
-
EffiNav: Fusing Depth and Vision-Language for Efficient Object Goal Navigation
EffiNav combines depth and vision-language inputs for efficient object goal navigation, matching or exceeding baselines on success rate and path-length-weighted success across simulation benchmarks and real-robot tests.
-
Vision-and-Language Navigation for UAVs: Progress, Challenges, and a Research Roadmap
A survey of UAV vision-and-language navigation that establishes a methodological taxonomy, reviews resources and challenges, and proposes a forward-looking research roadmap.
- Planning-aligned Token Compression for Long-Context Autonomous Driving
- GS-Playground: A High-Throughput Photorealistic Simulator for Vision-Informed Robot Learning