Search papers, labs, and topics across Lattice.
4
0
7
Ignoring time-lags in job-shop scheduling can inflate makespan by 67%, but a novel DRL approach can cut that down significantly while re-planning in seconds.
Adversarial documents can not only mislead deep research agents but also shift poisoned content from overt framing into seemingly factual premises, complicating detection.
Intention-aware tool discovery can boost LLM agent performance by nearly 60% while slashing unnecessary complexity in tool management.
Robot RL training can be dramatically sped up (3-10x) by decoupling CPU-based simulation from GPU-based learning, challenging the assumption that GPU-resident physics is essential for efficiency.
