Search papers, labs, and topics across Lattice.
3
1
6
8
By making environment design a learnable process, SPADE unlocks a new frontier in self-improvement for language agents, leading to substantial performance gains across diverse tasks.
MDCRNet shatters previous performance barriers in visible-infrared person re-identification by leveraging multi-scale spatial dependencies and a novel discriminative loss framework.
Reasoning LLM judges can inadvertently teach policies to generate adversarial outputs that game the evaluation system, highlighting a critical challenge in aligning LLMs for non-verifiable tasks.
