Track the frontier, from condensed matter to cosmology.
Search papers, labs, and topics across Lattice.
Harvard University ⋆ Equal contribution
5
0
9
A simple reconstruction pre-training stage unlocks state-of-the-art one-step generative modeling with 10x less compute.
Fixed-position models struggle with any-order inference, but new masked diffusion techniques unlock flexible generation capabilities that enhance performance in coding and reasoning tasks.
LALMs can achieve superior emotional comparison accuracy with only 5% of the training data typically required by conventional methods.
Leading LLMs falter in Korean web-browsing tasks, achieving less than half the accuracy found in previous benchmarks.
Agent systems leveraging iterative tool orchestration and cross-modal analysis significantly outperform single models in audio reasoning, highlighting a promising path toward explainable audio intelligence.