Search papers, labs, and topics across Lattice.
6
0
9
0
Even the best LLMs struggle with Olympiad-level physics, achieving only 33.7% accuracy on a new benchmark that challenges their reasoning capabilities.
Achieving a median ground-truth relative error of only 0.70%, FormalAnalyticGeo revolutionizes the generation of multimodal analytic geometry problems without human intervention.
LLMs are evolving from reactive chatbots to proactive digital colleagues, fundamentally changing how AI can assist in complex tasks.
A new robustness metric based on Fisher Information reveals critical insights into model sensitivity and adversarial vulnerability across popular architectures.
Forget bolting vision onto language models – truly powerful multimodal AI demands rethinking architectures from the ground up.
Give your memory-less VLA policy a brain: TempoFit retrofits temporal context by cleverly reusing existing attention keys and values, boosting long-horizon task success without retraining or adding latency.
