Search papers, labs, and topics across Lattice.
3
0
7
This work introduces MAPLE (Memory-Augmented Planning with Language and Evolution), an agent for maintaining optimization problems through successive natural-language requests and introduces NLDO, a benchmark of 15 trajectories and 180 updates spanning selection, scheduling, rostering, routing, and cloud-resource placement.
LFPM achieves robust backdoor mitigation in model merging while maintaining clean-task performance, challenging the efficacy of traditional parameter-space defenses.
Even state-of-the-art vision-language models still struggle to reconcile visual evidence with commonsense, often hallucinating based on prior knowledge instead of what they actually see.
