Search papers, labs, and topics across Lattice.
4
0
7
Scammers exploit a systematic taxonomy of 18 scenarios, revealing how psychological techniques are strategically deployed to maximize their impact.
Training agents in MobileGym transfers surprisingly well to real-world mobile devices, retaining over 95% of the simulation-side performance gains.
LLMs can be made to reason much better by directly optimizing their pre-training output distribution, even before fine-tuning on specific tasks.
LLM agents can learn to continuously adapt and improve in complex environments by reflecting on past experiences and explicitly storing/retrieving reusable lessons, leading to substantial performance gains.
