Search papers, labs, and topics across Lattice.
Affiliation:
3
0
9
A small, training-free "brief thinker" can cut LLM reasoning tokens by 31% without sacrificing accuracy.
Current AI agents can match human performance in some tasks, but they largely recycle existing human-designed algorithms rather than creating novel solutions.
A single polluted web page can mislead LLM recommenders into promoting fake products, with up to 73.8% of recommendations compromised by just three manipulated results.
