Search papers, labs, and topics across Lattice.
2
0
5
5
Latent visual reasoning in multimodal LLMs is largely ineffective, as the "imagination" happening in latent space doesn't actually attend to the input or influence the output, making explicit text-based imagination a surprisingly better alternative.
By cleverly combining linear and softmax attention, HyTRec achieves state-of-the-art recommendation accuracy on long sequences while maintaining linear inference speed, resolving a key tradeoff in the field.
