Search papers, labs, and topics across Lattice.
4
0
6
4
IAR achieves a remarkable boost in retrieval-free question answering, outperforming traditional methods by effectively internalizing document knowledge into LLMs.
Achieving a 91.51% acceptable-answer rate in enterprise question answering reveals the potential of staged adaptation to balance proprietary knowledge acquisition with general capabilities.
ChartWalker reveals significant performance gaps in cross-chart RAG tasks, challenging the status quo of existing benchmarks and paving the way for more robust multi-modal reasoning.
MLLMs can now achieve over 7% better accuracy on mechanical drawing tasks, thanks to the new MechVQA dataset and the specialized MechVL model.
