Track synthesis, materials and catalysis as it is published.
Search papers, labs, and topics across Lattice.
Affiliation:
4
0
5
6
Beyond simple ranking, QD-Rec discovers a rich landscape of well-reasoned recommendations, revealing novel decision pathways previously obscured by standard recommender systems.
LLM agents can significantly outperform passive strategies in complex economic environments, but their success hinges on active communication and negotiation.
Open-weight models lag significantly behind proprietary counterparts on a new Japanese VQA benchmark, highlighting critical gaps in chart and table understanding.
Training VLMs on Jagle, the largest Japanese multimodal dataset, not only crushes existing models on Japanese tasks, but *also* boosts English performance when combined with English data.