Search papers, labs, and topics across Lattice.
Mohamed bin Zayed University of Artificial Intelligence
2
0
5
4
A simple training framework boosts pixel-level tampering detection performance in VLMs by over 26%, showcasing the power of balanced sampling and late-injection strategies.
Language agents can achieve more diverse and effective self-reflection by encoding cross-sample reflection patterns directly into model parameters, leading to significant performance gains in reasoning tasks.
