Search papers, labs, and topics across Lattice.
Affiliation:
3
0
5
5
Ancient-Bench reveals that even advanced models fail to solve the challenges of recognizing ancient Chinese texts, underscoring a critical gap in AI capabilities.
DiffMath achieves superior handwritten mathematical expression generation without costly spatial supervision, leveraging a novel latent diffusion approach that enhances both structure and accuracy.
Forget hand-crafted reward functions: $\text{RLR}^3$ leverages rubrics and LLMs to provide fine-grained, multi-criteria supervision, outperforming standard RLVR in vision-language tasks.
