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.
Large model empow- ered embodied ai: A survey on decision-making and embodied learning
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
GridS is a plug-and-play differentiable module for geometry-aware visual token resampling in VLA models that achieves under 10% token retention and 76% FLOPs reduction with no success-rate loss.
Proposes a structured concept-centric memory system for embodied agents that connects object, scene, transition, and skill memories to support coarse-to-fine retrieval and improve task performance over baselines.
Embodied AI requires treating privacy as a lifecycle architectural constraint rather than a stage-local feature, addressed via the proposed SPINE framework with a multi-criterion privacy classification matrix.
A survey of UAV vision-and-language navigation that establishes a methodological taxonomy, reviews resources and challenges, and proposes a forward-looking research roadmap.
A survey of physical AI that distinguishes theoretical physics reasoning from applied understanding and synthesizes advances in symbolic reasoning, embodied systems, and generative models to advocate for physics-grounded world models.
citing papers explorer
-
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.
-
See What Matters: Differentiable Grid Sample Pruning for Generalizable Vision-Language-Action Model
GridS is a plug-and-play differentiable module for geometry-aware visual token resampling in VLA models that achieves under 10% token retention and 76% FLOPs reduction with no success-rate loss.
-
Analytic Concept-Centric Memory for Agentic Embodied Manipulation
Proposes a structured concept-centric memory system for embodied agents that connects object, scene, transition, and skill memories to support coarse-to-fine retrieval and improve task performance over baselines.
-
Position: Embodied AI Requires a Privacy-Utility Trade-off
Embodied AI requires treating privacy as a lifecycle architectural constraint rather than a stage-local feature, addressed via the proposed SPINE framework with a multi-criterion privacy classification matrix.
-
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.
-
Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI
A survey of physical AI that distinguishes theoretical physics reasoning from applied understanding and synthesizes advances in symbolic reasoning, embodied systems, and generative models to advocate for physics-grounded world models.