Search papers, labs, and topics across Lattice.
University of Macau
4
1
6
11
GPT-5.5 not only tops the leaderboard in policy evolution but also reveals critical insights into how agents can optimize performance through strategic feedback utilization.
Literal translation biases dominate idiom translation in LLMs, but glosses can significantly enhance generation quality, revealing critical gaps in current models.
Even the best LLMs struggle with Olympiad-level combinatorics, achieving only 65.4% on a benchmark designed to expose their reasoning limitations.
LLM safety mechanisms are more vulnerable than we thought: psychological priming attacks achieve near-perfect success rates in eliciting harmful content across a wide range of models, including GPT-4o and Llama-3.2.
