Search papers, labs, and topics across Lattice.
5
0
10
1
ABot-N1 redefines urban navigation by achieving a 35% boost in point-of-interest arrival rates, setting new benchmarks for visual language navigation models.
Spectral analysis reveals hidden patterns in machine-generated text, enabling detection methods that are robust against adversarial attacks and domain shifts.
Current memory systems, despite their complexity, are surprisingly worse than naive RAG when applied to continuous lifelogging scenarios, revealing a critical need for better context preservation.
Skip the costly generative evals: a simple probe trained on internal LLM representations can accurately predict downstream task performance during training, slashing evaluation time from an hour to just three minutes.
Forget task-specific architectures: a single Vision-Language-Action foundation model, ABot-N0, now dominates embodied navigation across five distinct tasks.
