Search papers, labs, and topics across Lattice.
3
0
8
2
LLMs struggle to translate code into formal specifications, as evidenced by their poor performance on the new Model-Bench benchmark, revealing a critical gap in their ability to support formal verification.
DLLM inference gets a 2-8x speed boost without quality loss thanks to ReMix, a training-free method that cleverly mixes continuous representations into discrete decoding.
Debugging TLA+ specifications just got easier: ModelWisdom uses LLMs and interactive visualization to transform cryptic model-checker output into actionable insights.
