Search papers, labs, and topics across Lattice.
Southeast University
5
0
6
Stochastic modality masking during training can boost bimanual robotic manipulation success rates by over 30% without complex architectural changes.
Bridging the semantic-kinematic gap, GenPrior achieves unprecedented accuracy in zero-shot action recognition by integrating generative motion priors with textual embeddings.
Ability-guided transfer reveals that agents struggle to consistently leverage learned experiences, challenging the effectiveness of current self-evolution methods.
Backdoor attacks on self-supervised models can be effectively countered without any reliance on labels or training data, achieving substantial performance gains across multiple attack types.
Noise amplification reveals hidden artifacts in AI-generated videos, outperforming traditional detection methods by focusing on the nuances of noise rather than just visual content.
