Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
Affiliation:
3
0
6
Most LLM unlearning dissolves the moment a model is compressed for production, but isolating updates to high-significance layers prevents forgotten data from resurfacing under 4-bit quantization.
IntraShuffler cuts gradient recoverability by over 60%, thwarting privacy inference attacks in federated learning without sacrificing model performance.
Existing LLM watermarking schemes crumble when text is short, but XMark maintains high decoding accuracy and text quality even with limited tokens.