Search papers, labs, and topics across Lattice.
4
0
8
20
Autoresearch agents can waste compute resolving the same issues repeatedly, but targeted interventions can dramatically enhance their efficiency and performance.
RL amplifies existing preferences in LLMs while also revealing previously hidden correct moves, reshaping our understanding of model training dynamics.
LCLMs redefine the efficiency of long-context inference, achieving superior compression without sacrificing model quality.
LLMs still fail to grasp research-level mathematics, with top models scoring below random chance when superficial pattern matching is removed, even with access to proof sketches.
