Search papers, labs, and topics across Lattice.
S-Lab, Nanyang Technological University
3
0
5
13
Current video generation models struggle with law-grounded reasoning, with the best achieving only 47% on the new Apple-PI benchmark.
The fragmented field of world modeling can now be unified under a "levels x laws" taxonomy, revealing critical gaps in autonomous model revision and decision-centric evaluation.
Current video benchmarks fail to capture the nuances of animation, but AnimationBench fills the gap by rigorously evaluating character consistency, motion, and style.
