activity
20242026
collaborators

10 papers

cs.CV2026

CoMo: Learning Continuous Latent Motion from Internet Videos for Scalable Robot Learning

Jiange Yang, Yansong Shi, Haoyi Zhu +6

Unsupervised learning of latent motion from Internet videos is crucial for robot learning. Existing discrete methods generally mitigate the shortcut learning caused by extracting e…

cs.RO2026

StaMo: Unsupervised Learning of Generalizable Robot Motion from Compact State Representation

Mingyu Liu, Jiuhe Shu, Hui Chen +6

A fundamental challenge in embodied intelligence is developing expressive and compact state representations for efficient world modeling and decision making. However, existing meth…

cs.CV2026

InternVideo-Next: Towards General Video Foundation Models without Video-Text Supervision

Chenting Wang, Yuhan Zhu, Yicheng Xu +6

Large-scale video-text pretraining achieves strong performance but depends on noisy, synthetic captions with limited semantic coverage, often overlooking implicit world knowledge s…

cs.RO2025

Learning Primitive Embodied World Models: Towards Scalable Robotic Learning

Qiao Sun, Liujia Yang, Wei Tang +12

While video-generation-based embodied world models have gained increasing attention, their reliance on large-scale embodied interaction data remains a key bottleneck. The scarcity,…

cs.CV2025

OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling

Yang Zhou, Yifan Wang, Jianjun Zhou +16

The field of 4D world modeling - aiming to jointly capture spatial geometry and temporal dynamics - has witnessed remarkable progress in recent years, driven by advances in large-s…

cs.RO2025

VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers

Yating Wang, Haoyi Zhu, Mingyu Liu +3

In this paper, we introduce an innovative vector quantization based action tokenizer built upon the largest-scale action trajectory dataset to date, leveraging over 100 times more…