The paper unifies emerging graph-based world models under a new paradigm and proposes a taxonomy organized by spatial, physical, and logical relational inductive biases.
hub
Embodied AI Agents: Modeling the World
23 Pith papers cite this work. Polarity classification is still indexing.
23
Pith papers citing it
hub tools
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
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.
COMAP co-evolves textual world models and agent policies for LLMs through on-policy self-distillation, yielding up to 16.75% relative gains on embodied planning, web navigation, and tool-use tasks.
A multi-agent video world model using simplex rotary agent encoding and sparse hub attention achieves better fidelity, controllability, and consistency than baselines while generalizing from 2 to 4 players.
SCRIPT presents a scalable diffusion policy with JAST-DiT architecture, nonlinear history conditioning, and RLHR post-training that claims to outperform prior methods on text alignment, motion quality, and physical realism while scaling on a 1200-hour dataset.
LLMs show a grounding gap with humans on abstract concepts, with property-generation correlations at most r=0.37 versus human-to-human r>0.9, though larger models align better on explicit rating tasks and internal SAE features capture some grounding dimensions.
VLA-ATTC equips VLA models with adaptive test-time compute via an uncertainty clutch and relative action critic, cutting failure rates by over 50% on LIBERO-LONG.
Sentinel-VLA adds metacognitive status monitoring to VLA models for on-demand reasoning and error recovery, reporting over 30% higher real-world task success than prior SOTA.
Vision-language models use semantic signals more than syntactic ones to bind words like 'image' to actual visual inputs, with implications for robustness in multimodal systems.
AgentComm achieves nearly 50% bandwidth reduction in embodied agent communication via LLM semantic processing, importance-aware transmission, and a task knowledge base, with negligible impact on task completion.
Morphology-conditioned quadrupedal world model enables zero-shot generalization to new robot embodiments for locomotion tasks.
GraphThinker reduces temporal hallucinations in video reasoning by constructing event-based scene graphs and applying visual attention rewards in reinforcement finetuning.
VisPhyWorld evaluates MLLMs' physical reasoning via executable code generation for video reconstruction, with VisPhyBench showing strong semantics but weak parameter inference and dynamics simulation.
SpeechLess enables micro-utterance AR interactions by binding prior interactions to personal spatial context for intent extrapolation.
A three-stage training pipeline internalizes world-model simulation and success estimation in LLM agents for improved planning on search and math tasks.
IndustryAssetEQA integrates episodic telemetry representations with an FMEA knowledge graph to support embodied question answering over industrial assets, showing large gains in validity and reduced overclaims versus LLM baselines.
An empirical study of JEPA world models identifies architecture, training objective, and planning choices that yield a model outperforming DINO-WM and V-JEPA-2-AC on navigation and manipulation tasks.
Proposes a four-layer hierarchical communication architecture for 6G-enabled human-robot interaction and shows feasibility via a 5G-based prototype with millisecond latency and stable operation.
An agentic framework generates executable physics simulation code from text prompts via coordinated planning, coding, visual, and physics agents that iterate to satisfy both prompt fidelity and physical constraints.
Human-AI coexistence is best modeled as conditional mutualism under governance, formalized as a multiplex dynamical system whose simulations show stable high-coexistence equilibria only under balanced institutional oversight.
A systematic review of resource consumption threats in LLMs that organizes the problem along the full pipeline from threat induction to mitigation.
citing papers explorer
-
Graph World Models: Concepts, Taxonomy, and Future Directions
The paper unifies emerging graph-based world models under a new paradigm and proposes a taxonomy organized by spatial, physical, and logical relational inductive biases.
-
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.
-
COMAP: Co-Evolving World Models and Agent Policies for LLM Agents
COMAP co-evolves textual world models and agent policies for LLMs through on-policy self-distillation, yielding up to 16.75% relative gains on embodied planning, web navigation, and tool-use tasks.
-
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players
A multi-agent video world model using simplex rotary agent encoding and sparse hub attention achieves better fidelity, controllability, and consistency than baselines while generalizing from 2 to 4 players.
-
SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-based Humanoid Control
SCRIPT presents a scalable diffusion policy with JAST-DiT architecture, nonlinear history conditioning, and RLHR post-training that claims to outperform prior methods on text alignment, motion quality, and physical realism while scaling on a 1200-hour dataset.
-
The Grounding Gap: How LLMs Anchor the Meaning of Abstract Concepts Differently from Humans
LLMs show a grounding gap with humans on abstract concepts, with property-generation correlations at most r=0.37 versus human-to-human r>0.9, though larger models align better on explicit rating tasks and internal SAE features capture some grounding dimensions.
-
VLA-ATTC: Adaptive Test-Time Compute for VLA Models with Relative Action Critic Model
VLA-ATTC equips VLA models with adaptive test-time compute via an uncertainty clutch and relative action critic, cutting failure rates by over 50% on LIBERO-LONG.
-
Sentinel-VLA: A Metacognitive VLA Model with Active Status Monitoring for Dynamic Reasoning and Error Recovery
Sentinel-VLA adds metacognitive status monitoring to VLA models for on-demand reasoning and error recovery, reporting over 30% higher real-world task success than prior SOTA.
-
Source-Modality Monitoring in Vision-Language Models
Vision-language models use semantic signals more than syntactic ones to bind words like 'image' to actual visual inputs, with implications for robustness in multimodal systems.
-
AgentComm: Semantic Communication for Embodied Agents
AgentComm achieves nearly 50% bandwidth reduction in embodied agent communication via LLM semantic processing, importance-aware transmission, and a task knowledge base, with negligible impact on task completion.
-
Toward Hardware-Agnostic Quadrupedal World Models via Morphology Conditioning
Morphology-conditioned quadrupedal world model enables zero-shot generalization to new robot embodiments for locomotion tasks.
-
GraphThinker: Reinforcing Temporally Grounded Video Reasoning with Event Graph Thinking
GraphThinker reduces temporal hallucinations in video reasoning by constructing event-based scene graphs and applying visual attention rewards in reinforcement finetuning.
-
VisPhyWorld: Probing Physical Reasoning via Code-Driven Video Reconstruction
VisPhyWorld evaluates MLLMs' physical reasoning via executable code generation for video reconstruction, with VisPhyBench showing strong semantics but weak parameter inference and dynamics simulation.
-
SpeechLess: Micro-utterance with Personalized Spatial Memory-aware Assistant in Everyday Augmented Reality
SpeechLess enables micro-utterance AR interactions by binding prior interactions to personal spatial context for intent extrapolation.
-
Internalizing the Future: A Unified Agentic Training Paradigm for World Model Planning
A three-stage training pipeline internalizes world-model simulation and success estimation in LLM agents for improved planning on search and math tasks.
-
IndustryAssetEQA: A Neurosymbolic Operational Intelligence System for Embodied Question Answering in Industrial Asset Maintenance
IndustryAssetEQA integrates episodic telemetry representations with an FMEA knowledge graph to support embodied question answering over industrial assets, showing large gains in validity and reduced overclaims versus LLM baselines.
-
6G Communication Networks Enabling Embodied Agents: Architecture and Prototype
Proposes a four-layer hierarchical communication architecture for 6G-enabled human-robot interaction and shows feasibility via a 5G-based prototype with millisecond latency and stable operation.
-
Coding Agent Is Good As World Simulator
An agentic framework generates executable physics simulation code from text prompts via coordinated planning, coding, visual, and physics agents that iterate to satisfy both prompt fidelity and physical constraints.
-
A Co-Evolutionary Theory of Human-AI Coexistence: Mutualism, Governance, and Dynamics in Complex Societies
Human-AI coexistence is best modeled as conditional mutualism under governance, formalized as a multiplex dynamical system whose simulations show stable high-coexistence equilibria only under balanced institutional oversight.
-
Resource Consumption Threats in Large Language Models
A systematic review of resource consumption threats in LLMs that organizes the problem along the full pipeline from threat induction to mitigation.
- OpenWorldLib: A Unified Codebase and Definition of Advanced World Models
- Controllable Egocentric Video Generation via Occlusion-Aware Sparse 3D Hand Joints