3 papers
cs.CV2026
Mem-World: Memory-Augmented Action-Conditioned World Models for Persistent Robot Manipulation
Zirui Zheng, Jiaqian Yu, Xiongfeng Peng +7
Action-conditioned world models have emerged as a promising paradigm for robot learning, offering a scalable alternative to costly real-world experimentation by generating action-c…
cs.CV2026
HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
Team HY-World, Chenjie Cao, Xuhui Zuo +42
We introduce HY-World 2.0, a multi-modal world model framework that advances our prior project HY-World 1.0. HY-World 2.0 accommodates diverse input modalities, including text prom…
cs.CV2025
EvolvingGS: High-Fidelity Streamable Volumetric Video via Evolving 3D Gaussian Representation
Chao Zhang, Yifeng Zhou, Shuheng Wang +4
We have recently seen great progress in 3D scene reconstruction through explicit point-based 3D Gaussian Splatting (3DGS), notable for its high quality and fast rendering speed. Ho…