Search papers, labs, and topics across Lattice.
3
0
6
12
Most web-browsing LLM agents struggle to find obscure, multi-hop information across diverse modalities and languages, even when explicitly designed for web interaction.
Stronger reasoning in LLMs using Code Interpreters hinges on the strategic use of crucial tokens and cognitive behaviors, revealing both potential and constraints in model performance.
Fine-tuning VLMs for regional relevance doesn't have to sacrifice global performance: a simple data filtering and model merging technique boosts cultural relevance by 5-15% while barely impacting overall accuracy.
