✨ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction

📝 Summary:
ENACT is a benchmark evaluating embodied cognition in vision-language models through egocentric world modeling tasks. It reveals a performance gap between VLMs and humans that widens with interaction, and models exhibit anthropocentric biases.

🔹 Publication Date: Published on Nov 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.20937
• PDF: https://arxiv.org/pdf/2511.20937

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#EmbodiedCognition #VisionLanguageModels #AIResearch #WorldModeling #CognitiveScience

🔥 stable-worldmodel-v1: Reproducible World Modeling Research and Evaluation

💡 The paper introduces stable-worldmodel, a modular and standardized research framework for developing and evaluating world models. World models are a powerful tool for learning compact representations of environment dynamics, enabling agents to reason and generalize beyond direct experience. However, current implementations are often publication-specific, which limits their reusability, increases the risk of bugs, and reduces evaluation standardization.

To address this issue, the authors developed stable-worldmodel, a tested and documented research ecosystem that provides efficient data collection tools, standardized environments, planning algorithms, and baseline implementations. The framework allows for controllable environmental factors, including visual and physical properties, to support robustness and continual learning research.

The authors demonstrate the utility of stable-worldmodel by using it to study zero-shot robustness in DINO-WM. The framework provides a standardized way to evaluate world models, which can help to advance research in this area. The main contributions of the paper are the introduction of a modular and standardized research framework for world models, the provision of efficient data collection tools and standardized environments, and the demonstration of the framework's utility in studying zero-shot robustness.

Overall, the paper aims to provide a reliable and reproducible research framework for world modeling, which can help to accelerate progress in this field. The authors' goal is to enable researchers to focus on developing new world models and evaluating their performance, rather than spending time on implementing and debugging existing models. By providing a standardized framework, the authors hope to facilitate the development of more robust and generalizable world models that can be used in a variety of applications.

📅 Published on Feb 9

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2602.08968
• PDF: https://arxiv.org/pdf/2602.08968
• Project Page: https://galilai-group.github.io/stable-worldmodel/

🤖 Models citing this paper:
• https://huggingface.co/zzsi/swm-dmc-cheetah
• https://huggingface.co/zzsi/swm-dmc-expert-policies

📊 Datasets citing this paper:
• https://huggingface.co/datasets/zzsi/swm-dmc-expert
• https://huggingface.co/datasets/zzsi/swm-dmc-mixed-small
• https://huggingface.co/datasets/zzsi/swm-dmc-mixed-large

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://xn--r1a.website/PaperNexus

#WorldModeling #ReinforcementLearning #ArtificialIntelligence #RoboticsResearch #EnvironmentModeling

🔥 Kairos: A Native World Model Stack for Physical AI

💡 The paper introduces Kairos, a native world model framework designed to support physical AI applications. The problem addressed is that current world models are limited in their ability to learn from diverse experiences, maintain persistent states over time, and deploy efficiently in real-world scenarios. To address this, Kairos pioneers a native pre-training paradigm that learns from open-world videos, human behavioral data, and robot interactions, organized into a progressive developmental pathway.

The method involves a native unified architecture equipped with hybrid linear temporal attention, which captures local dynamics, mid-range dependencies, and maintains persistent global memory. This architecture is designed to limit error accumulation and guarantee state propagation across extended horizons. Additionally, Kairos incorporates a deployment-aware system co-design to support low-latency rollout generation on various hardware platforms.

The results show that Kairos achieves top-level performance on embodied world-model, long-horizon, and action-policy benchmarks, while offering a strong efficiency-capability trade-off. The experiments demonstrate that Kairos can learn from diverse experiences, maintain persistent states, and deploy efficiently in real-world scenarios. Overall, the paper positions Kairos as a cohesive operational foundation for future self-evolving physical intelligence, providing a native world model stack that can support a wide range of physical AI applications.

📅 Published on Jun 16

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2606.16533
• PDF: https://arxiv.org/pdf/2606.16533

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://xn--r1a.website/PaperNexus

#PhysicalAI #WorldModeling #NativePreTraining #RobotLearning #TemporalAttention

🔥 Quo Vadis, World Modeling?

💡 The paper Quo Vadis, World Modeling discusses the limitations of current world modeling approaches in providing feedback to agents that require dynamic interaction beyond static supervision. Direct real environment interaction is costly, slow, unsafe, and hard to parallelize, making world modeling a natural intermediate proxy that allows agents to query lower cost and more controllable feedback before committing to real actions.

The authors conceptualize Agent-Centric Interactive World Proxies, shifting the fundamental paradigm from physical state transitions to agent usable information transitions, such as execution outcomes, retrieved experiences or skills, and verification signals. This broadens the scope of world modeling to provide versatile feedback for continuously improving agents.

The authors systematically map this design space by organizing world proxies into six functional forms based on their feedback modalities: dynamics, spatial, execution, memory/experience, skill, and reward/verification proxies. These proxies characterize the primary ways world modeling serves agent improvement.

The authors further analyze how these proxies empower agents across three progressive levels: Level 1 Inference-Time Guidance, where proxy outputs enrich in-context information for superior decisions; Level 2 Training-Time Optimization, where proxy outputs yield rewards, critiques, or synthetic rollouts for policy learning; and Level 3 Agent-Proxy Co-Evolution, where real environment evidence continuously updates both the proxy and the agent for co-evolution.

Ultimately, the paper recasts world modeling into an agent-centric paradigm, establishing a roadmap for building world proxies that empower agents to plan better, learn faster, and evolve continuously. The authors provide a framework for designing and analyzing world models that can provide effective feedback to agents, enabling them to improve their performance and adapt to changing environments.

📅 Published on Aug 3

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2608.02713
• PDF: https://arxiv.org/pdf/2608.02713
• Project Page: https://worldbench.github.io/awesome-agentic-world-model

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://xn--r1a.website/PaperNexus

#WorldModeling #AgentCentricProxies #InteractiveWorldProxies #DynamicInteraction #ArtificialIntelligence