aiqbench analysis
MIND-V addresses the scarcity of long-horizon robotic data by combining hierarchical reasoning with a reinforcement learning post-training phase guided by a physics-aware reward function. This approach enables the synthesis of physically plausible, long-duration manipulation videos, offering a scalable framework for autonomous embodied data generation. The method's reliance on V-JEPA2 as a physics referee highlights a practical integration of world models to enforce dynamic consistency in latent spaces.
MIND-V: Hierarchical World Model for Long-Horizon Robotic Manipulation with RL-based Physical Alignment
arXiv:2512.06628v3 Announce Type: replace Abstract: Scalable embodied intelligence is constrained by the scarcity of diverse, long-horizon robotic manipulation data. Existing video world models in this domain are limited to synthesizing short clips of simple actions and often rely on manually defined trajectories. To this end, we introduce MIND-V, a cognitive hierarchical world model designed to synthesize physically plausible and logically coherent videos of long-horizon robotic manipulation. Inspired by cognitive science, MIND-V bridges high-level reasoning with pixel-level synthesis through three core components: a Semantic Reasoning Hub (SRH) that leverages a pre-trained vision-language model for task planning; a Behavioral Semantic Bridge (BSB) that translates abstract instructions into domain-invariant representations; and a Motor Video Generator (MVG) for conditional video rendering. MIND-V employs Staged Visual Future Rollouts, a test-time optimization strategy to enhance long-horizon robustness. To enforce adherence to physical laws, we introduce a GRPO reinforcement learning post-training phase guided by a novel Physical Foresight Coherence (PFC) reward. PFC leverages the V-JEPA2 world model as a physics referee to penalize implausible dynamics in the latent feature space. Experiments confirm MIND-V's SOTA performance in long-horizon simulation and its significant value for policy learning, introducing a scalable and fully autonomous framework for embodied data synthesis.
Abstract:Scalable embodied intelligence is constrained by the scarcity of diverse, long-horizon robotic manipulation data. Existing video world models in this domain are limited to synthesizing short clips of simple actions and often rely on manually defined trajectories. To this end, we introduce MIND-V, a cognitive hierarchical world model designed to synthesize physically plausible and logically coherent videos of long-horizon robotic manipulation. Inspired by cognitive science, MIND-V bridges high-level reasoning with pixel-level synthesis through three core components: a Semantic Reasoning Hub (SRH) that leverages a pre-trained vision-language model for task planning; a Behavioral Semantic Bridge (BSB) that translates abstract instructions into domain-invariant representations; and a Motor Video Generator (MVG) for conditional video rendering. MIND-V employs Staged Visual Future Rollouts, a test-time optimization strategy to enhance long-horizon robustness. To enforce adherence to physical laws, we introduce a GRPO reinforcement learning post-training phase guided by a novel Physical Foresight Coherence (PFC) reward. PFC leverages the V-JEPA2 world model as a physics referee to penalize implausible dynamics in the latent feature space. Experiments confirm MIND-V's SOTA performance in long-horizon simulation and its significant value for policy learning, introducing a scalable and fully autonomous framework for embodied data synthesis.
Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
arXiv:2512.06628 [cs.RO]
(or arXiv:2512.06628v3 [cs.RO] for this version)
Full text under the publisher's open licence · 210 words
Related coverage
Dyna-2: General Purpose Physical Agents with Hour-Long Autonomy — Jason Ma, Dyna Robotics
Latent Space · Oct 13, 2026
The J-Space Debate, Agent Swarms, and Pacing Frontier AI - Digital Minds Newsletter #4
LessWrong · Sep 18, 2026
$\tau_0$-VLA: a Hierarchical Robot Foundation Model with World-Model-Guided Test-Time Computation
arXiv · Aug 18, 2026
HiMem-WAM: Hierarchical Memory-Gated World Action Models for Robotic Manipulation
arXiv · Jun 10, 2026