Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
Affiliation:
3
0
3
28
Even with extensive biological context, large language models struggle to consistently improve cellular response predictions, suggesting current evidence integration methods are insufficient for complex biological reasoning.
Tree search methods can significantly enhance reasoning in LLMs, revealing that traditional decoding approaches may be holding back their potential.
SciReasoner achieves a remarkable 31% improvement in Cellular Component annotation for low-homology proteins, showcasing the power of structural reasoning in AI.