Search papers, labs, and topics across Lattice.
2
0
4
Adversarial images in CLIP reveal a consistent directional bias that can be exploited to enhance model robustness, leading to surprising cases where adversarial accuracy surpasses clean accuracy.
Current AI agents struggle to reliably rediscover scientific knowledge, with top performers averaging only 21.5 out of a possible score, revealing critical gaps in their research capabilities.
