Search papers, labs, and topics across Lattice.
Nankai University
5
0
5
GAINS reveals that effectively modeling human imperfection can boost task success rates by over 20% in robot manipulation tasks.
Multi-dimensional Evaluation-Verification Reward transforms multi-reference image editing by providing a structured approach to evaluate and enhance visual consistency, yielding superior results over existing models.
Aesthetic assessments can be dramatically improved by focusing on key moments and endings, as shown by Peak-End-Net's state-of-the-art results in video evaluation.
Achieving an overall score of 84.76, DreamX-World 1.0 sets a new benchmark for interactive video generation, outperforming leading models in both camera control and visual fidelity.
Video diffusion models can achieve superior human motion control by leveraging 3D mesh tokenization, revealing a deeper understanding of 3D structures than previously thought.
