Search papers, labs, and topics across Lattice.
Shanghai AI Laboratory
5
0
8
Models with similar success rates can have drastically different capability profiles, revealing hidden strengths and weaknesses in mobile manipulation tasks.
Aggregating insights from diverse causal discovery experts with LLM-guided reweighting leads to significantly improved causal graph accuracy, even in ambiguous scenarios.
LLM uncertainty can be efficiently estimated *without* sampling by measuring the stability of output distributions under semantically equivalent input perturbations.
Log-based anomaly detection models are missing 90% of the picture, but AnomalyGen uses LLMs and static analysis to hallucinate realistic training data and close the gap.
LLMs can now explain chemical reactions from 4D molecular trajectories, thanks to a new benchmark and model designed to bridge the gap between dynamic molecular simulations and natural language understanding.
