Search papers, labs, and topics across Lattice.
University of Illinois Chicago
2
0
5
4
Even state-of-the-art LLMs struggle to adapt to mid-task changes in long-horizon web navigation, highlighting a critical gap in their ability to handle realistic user interactions.
Stop hand-crafting RLHF curricula: ACTOR-CURATOR learns to dynamically select training problems, boosting performance by up to 30% and speeding up training by 80% on challenging reasoning tasks.
