Search papers, labs, and topics across Lattice.
5
0
11
0
Personalized privacy budgets in decentralized graph learning can significantly enhance data utility while safeguarding sensitive information.
Achieve robust LVLM defense against adversarial attacks with minimal image modification and computational cost by exploiting structural priors.
Seedance 2.0 leapfrogs existing models by unifying multi-modal inputs (text, image, audio, video) into a single architecture for generating high-quality, longer-duration audio-video content.
Forget brittle fact memorization – CoT2Edit teaches LLMs to *reason* their way to updated knowledge, unlocking robust generalization in real-world scenarios.
Resource consumption vulnerabilities in LLMs can lead to degraded service availability and economic sustainability, demanding a systematic understanding and mitigation approach.
