STRNet improves goal-conditioned visual navigation by replacing simplistic encoders and pooling with a spatio-temporal fusion module that performs spatial graph reasoning and hybrid temporal modeling.
Navidiffusor: Cost-guided diffusion model for visual navigation.arXiv preprint arXiv:2504.10003
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
MATT-Diff uses a diffusion model with vision transformer and attention to generate multimodal actions for active multi-target tracking from expert planner demonstrations.
A diffusion-based 4D trajectory predictor with dimension decoupling and residual refinement, integrated into DNMPC, reduces UAV swarm tracking error by 10-15% while running at 34 FPS on a new multi-scenario dataset.
RoamFlow applies MeanFlow to predict average velocity fields for one-step action policies in image-goal navigation, trained via expert imitation followed by RL refinement.
ORION applies ordinal neural collapse to organize visual encoder features along an action-ordinal axis, then integrates the encoder into a diffusion navigation policy, yielding higher success rates than end-to-end and standard neural collapse baselines in simulation and real-world tests.
citing papers explorer
-
MATT-Diff: Multimodal Active Target Tracking by Diffusion Policy
MATT-Diff uses a diffusion model with vision transformer and attention to generate multimodal actions for active multi-target tracking from expert planner demonstrations.
-
Diffusion-based 4D Trajectory Prediction and Distributed Control for UAV Swarms
A diffusion-based 4D trajectory predictor with dimension decoupling and residual refinement, integrated into DNMPC, reduces UAV swarm tracking error by 10-15% while running at 34 FPS on a new multi-scenario dataset.
-
RoamFlow: Reinforcement-Aligned One-Step Action MeanFlow Policy for Image-Goal Navigation
RoamFlow applies MeanFlow to predict average velocity fields for one-step action policies in image-goal navigation, trained via expert imitation followed by RL refinement.
-
Ordinal Neural Collapse as a Representation Prior for Visual Navigation
ORION applies ordinal neural collapse to organize visual encoder features along an action-ordinal axis, then integrates the encoder into a diffusion navigation policy, yielding higher success rates than end-to-end and standard neural collapse baselines in simulation and real-world tests.