5 papers · 1 filter
Video2World: Benchmarking Coding Agents for Interactive World Modeling from Embodied Videos
Jinzhou Tang, Zijun Zhang, Jing Yang +10
Building interactive simulators from real-world observations is a promising way to scale embodied data, but current pipelines still rely heavily on manual environment construction…
DeTrack: A Benchmark and Altitude-Aware Dual World Model for Drone-embodied Tracking
Guyue Hu, Haoming Liu, Siyuan Song +3
Aerial object tracking has broad applications in public safety, emergency rescue, wildlife monitoring, and related fields. However, existing aerial tracking benchmarks are mainly b…
LASAR: Towards Spatio-temporal Reasoning with Latent Cognitive Map
Jinzhou Tang, Sidi Liu, Waikit Xiu +2
A fundamental challenge in embodied AI is verifying if agents build internal models of spatial structure or merely learn to mimic task-specific expert trajectories. This is critica…
DreamSAC: Learning Hamiltonian World Models via Symmetry Exploration
Jinzhou Tang, Fan Feng, Minghao Fu +3
Learned world models excel at interpolative generalization but fail at extrapolative generalization to novel physical properties. This limitation arises because they learn statisti…
Beyond Pixels: Introducing Geometric-Semantic World Priors for Video-based Embodied Models via Spatio-temporal Alignment
Jinzhou Tang, Jusheng zhang, Sidi Liu +3
Achieving human-like reasoning in deep learning models for complex tasks in unknown environments remains a critical challenge in embodied intelligence. While advanced vision-langua…