Search papers, labs, and topics across Lattice.
4
0
5
4
Most video generation models fail to render text accurately, with even top performers exhibiting a 25% word error rate on a new benchmark designed for this critical oversight.
Not every missing modality needs to be repaired for optimal sentiment analysis, and SIEVE learns to make this decision dynamically at the sample level.
GUI agents struggle with long tasks not because they mis-click, but because they forget what they were doing, and a new "anchored memory" method can fix it.
Video fine-tuning boosts MLLMs' video smarts, but surprisingly dumbs them down on static images – a trade-off you can't simply brute-force away with more frames.
