Search papers, labs, and topics across Lattice.
Affiliation:
4
0
4
13
UniTraffic-Agent achieves top-tier performance in complex traffic video reasoning tasks, showcasing the potential of structured workflows in multimodal AI applications.
GoodDiffusion's innovative use of learnable signatures can thwart unauthorized access while preserving high-quality outputs for legitimate users, a game-changer for copyright protection in generative models.
Subtle and rare mistakes in egocentric videos can be detected with unprecedented accuracy by fusing insights from both coarse and fine action analyses.
Naive combinations of diffusion and contrastive learning suffer from gradient conflict, but injecting contrastive signals from reconstructed images can jointly optimize discriminative and perceptual abilities in CLIP visual encoders.
