Search papers, labs, and topics across Lattice.
Affiliation:
4
0
6
2
SemaPLC achieves a remarkable 52.2% dynamic behavior score, setting a new standard for verifying the operational integrity of PLC code generation.
A 7B parameter model, optimized with multi-task learning and RL, rivals the timeline summarization performance of a 671B parameter model, proving that task-specific fine-tuning can dramatically shrink model size without sacrificing quality.
Sema Code unlocks AI coding agents from specific interfaces, offering a programmable core that can be embedded into any runtime environment.
Open-source SemaClaw offers a blueprint for building production-ready personal AI agents, shifting the focus from raw model capabilities to robust harness engineering.
