Search papers, labs, and topics across Lattice.
2
0
5
3
Robust-TO not only boosts video reasoning accuracy by over 10% but also minimizes performance drops under real-world visual distortions.
Video reasoning models can suffer up to a 35% drop in accuracy and 28% in reasoning quality under real-world perturbations, but a new training framework, ROVA, mitigates this by adaptively prioritizing informative samples.
