Search papers, labs, and topics across Lattice.
Monash University
3
0
7
Forget costly training or reward models: MATO unlocks personalized LLM alignment by optimizing objective weights *during* generation, offering unprecedented control and adaptability.
LLMs struggle to balance task completion with cultural norms in dynamic social simulations, revealing critical gaps in their cross-cultural robustness and highlighting the need for human oversight in automated benchmarking.
Forget random noise – teaching models *how* to explore their reasoning process yields more reliable inference-time scaling.
