Search papers, labs, and topics across Lattice.
8
0
10
2
BrainPilot achieves state-of-the-art performance in brain science research automation while maintaining rigorous auditability and cost-effectiveness.
Evolving rubrics from a single query can dramatically enhance LLM evaluation by eliminating reliance on external annotations and improving answer quality discrimination.
Current LLMs achieve only 50.64% accuracy on a new benchmark for higher-order logical reasoning, revealing a critical gap in their reasoning capabilities.
TriFlow achieves 90% lower Chamfer Distance and 8x faster mesh generation, setting a new standard for artist-like 3D topology synthesis.
BestMan enables seamless integration of real-world observations into simulation, revolutionizing how mobile manipulators learn and adapt in unstructured environments.
Surpassing existing methods, Orchestra-o1 achieves a 10.3% accuracy improvement on the OmniGAIA benchmark by enabling seamless collaboration across multiple modalities.
Aggregating insights from diverse causal discovery experts with LLM-guided reweighting leads to significantly improved causal graph accuracy, even in ambiguous scenarios.
Struct-Searcher achieves a remarkable 17.2% accuracy boost in multimodal information seeking by effectively managing conflicting evidence through a dynamic structural graph.
