Search papers, labs, and topics across Lattice.
4
0
8
0
Current benchmarks miss the point: the real value of AI peer review lies in the quality of its textual justification, not just predicting a rating.
LLMs can learn to avoid repeating mistakes by remembering and penalizing frequently recurring error patterns in past rollouts.
Forget benchmarks: AI can now learn "scientific taste" and propose research ideas with higher potential impact than humans, thanks to a novel reinforcement learning approach using citation data.
LLMs can be made better software engineers by pre-training them to reconstruct the messy, iterative development process that led to the final, clean code in repositories.
