Search papers, labs, and topics across Lattice.
3
0
7
12
Forget task-specific fine-tuning – teaching VLMs basic geometry yields a +29% boost on spatial reasoning benchmarks.
RL fine-tuning can nearly double the performance of LLM agents on complex, multi-step spreadsheet tasks, suggesting a promising path towards automating real-world data-centric workflows.
Vision models are far more data-hungry than language models, but Mixture-of-Experts can harmonize this asymmetry for truly unified multimodal models.
