Search papers, labs, and topics across Lattice.
2
0
5
5
Stop reinventing the wheel for diffusion LLM alignment: DARE provides a unified framework for SFT, preference optimization, and RL, accelerating research and enabling fair comparisons across dLLMs.
DeepSight offers an all-in-one open-source toolkit for LLM safety, promising to move beyond black-box evaluations and provide white-box insights into internal mechanisms.
