Tag
Introduces MASC (Margin Self-Correction), an efficient unlearning method for LLMs that uses an online stopping rule to achieve competitive forget–retain trade-offs at reduced computational cost, validated on TOFU and MUSE benchmarks.
This paper introduces inner product aware quantization methods that preserve inner products with unseen vectors, developing fast and adaptive algorithms with provable guarantees, achieving 2-10x speedup over prior ASQ methods.
The creator of SubQ announces an overwhelming response to the SSA breakthrough, with plans to release a model card with additional data and third-party validation next week.