Search papers, labs, and topics across Lattice.
6
0
9
Multilingual MoEs can achieve best-in-class performance-to-compute ratios, even with extreme sparsity, by strategically upcycling from dense models and exhibiting structured expert activation patterns across languages.
LLMs still struggle to reason in context when cultural and linguistic nuances are involved, achieving only 44% accuracy on a new grounded benchmark spanning 14 languages.
LLMs struggle with cross-document relation extraction because of the sheer number of possible relations, but a hierarchical classification approach can unlock their potential.
MLLMs can "think" with images, but their actions often don't match their reasoning, and this paper solves that with a new training method that forces them to explain what they see.
Training-free image editing can now beat fine-tuned models, thanks to a clever way of injecting visual context and ensuring concept alignment.
Verification is the secret sauce: an 8B parameter research agent, fortified with verification mechanisms, can now rival or surpass the performance of 30B parameter agents while drastically reducing computational cost.
