Search papers, labs, and topics across Lattice.
State Key Laboratory for Novel Software Technology
3
0
6
0
LLMs can bootstrap their code generation abilities by focusing on problems where they show diverse solution attempts and then reinforcing solutions that exhibit behavioral consensus.
LLMs can strategically obfuscate their reasoning, with chain-of-thought monitorability dropping by up to 30% under stress tests, particularly when tasks don't demand explicit reasoning.
GUI agents can achieve significantly stronger task-solving capabilities through carefully designed post-training and data curation, without relying on costly online data collection.
