Search papers, labs, and topics across Lattice.
University of Electronic Science and Technology
4
0
8
Unlearning sensitive information in LLMs can be achieved without sacrificing performance, with ADU preserving up to 98% of model utility while effectively forgetting.
EAMP boosts robotic navigation safety by dynamically adapting to unforeseen events, achieving superior performance without sacrificing real-time responsiveness.
Forget noisy raw history: MemRerank distills user purchase history into concise, query-independent signals, boosting personalized product reranking by over 10%.
Achieve >95% forget quality in LLMs with minimal side effects by isolating and unlearning tokens within target subdomains using asymmetric LoRA.
