Search papers, labs, and topics across Lattice.
2
0
4
MLLMs struggle to plan coherent interleaved text-and-image generation, often missing opportunities for tool use, revealing a critical gap in their ability to unify factuality with creativity.
Forget expensive LLM-as-judge checks: Proxy-GRM learns transferable rubrics for vision-language reward models with a lightweight proxy, achieving SOTA results with 4x less data.
