Search papers, labs, and topics across Lattice.
POSTECH, Pohang University of Science and Technology (POSTECH) 2 RLWRLD Abstract Forecasting dynamic scenes remains a fundamental challenge in computer vision, as limited observations make it difficult to capture coherent object-level motion and long-term temporal evolution. We present Motion Group-aware Gaussian Forecasting (MoGaF), a framework for long-term scene extrapolation built upon the
1
0
3
4
Planning in latent world models just got 10x faster: CompACT compresses observations into only 8 tokens without sacrificing performance.
