Search papers, labs, and topics across Lattice.
4
0
8
LongRTL's innovative use of graph similarity allows LLMs to optimize complex RTL designs while maintaining functional integrity across long contexts.
By adversarially synthesizing graph structures and self-correcting node labels, AdvSynGNN achieves state-of-the-art robustness against structural noise and heterophily in graph neural networks.
Achieve robust multimodal sentiment analysis, even with noisy or incomplete data, by explicitly modeling hierarchical relationships in hyperbolic space.
Achieve a better trade-off between search precision and carbon footprint with GaiaFlow, a framework that uses semantic-guided diffusion tuning to make neural search systems more sustainable.
