Search papers, labs, and topics across Lattice.
4
4
9
4
A simple visual harness transforms a general multimodal model into a perfect reasoner on ARC-AGI-3, completing all games with drastically fewer actions than humans.
TSFT redefines how we allocate fine-tuning resources in CRL, achieving near-oracle performance while maximizing task coverage.
Automating freeway network extraction from OSM can cut analyst effort by two-thirds, making large-scale freeway simulations feasible.
LLM agents can autonomously outperform fixed evolutionary search by 3-10x on open-ended discovery tasks when given persistent memory, asynchronous collaboration, and heartbeat-based interventions.
