Pinned
1/ How can we make Low-Rank Matrices behave more like Full-Rank Matrices—and achieve higher rank efficiency?
We release our new paper: NoRA: Normalized Low-Rank Adaptation.
Paper: arxiv.org/abs/2608.31036
- The best peft paper I've ever read this year. alphaxiv.org/abs/2608.31036
- Effortless win — welcome everyone to try MiSS. Code for MiSS lossless LoRA conversion will be updated soon in PEFT, so you can easily adapt it to frameworks like vLLM and Slime.Accepted by ICML'26, c u @ Seoul ! Thanks for all the coauthors! #ICML
- MiSS achieves the optimal balance between efficiency and performance and has already topped the PEFT benchmark. We will update the experimental comparison between DoRA and MiSS under the same parameter in Parameter-Efficient Reinforcement Learning, and I believe MiSS will surpass
- Considering the trade-off between efficiency and performance, is DDL worth using? We need to know more about experiments related to computational overhead.Deep Delta Learning, WE COOKED! 🚀🚀🚀 yifanzhang-pro.github.io/deep-delta-lea…
