Mingxue (Mercy) Xu
LightNews LightNews
banner
mercyxu.bsky.social
Mingxue (Mercy) Xu
@mercyxu.bsky.social
170 followers 120 following 7 posts
PhD student at Imperial College London, generative (language) model compression with algebraic approaches.
https://mingxue-xu.github.io/
Posts Replies Media Videos
Pinned
mercyxu.bsky.social
Mingxue (Mercy) Xu @mercyxu.bsky.social · Apr 11
Slightly lazy but feel need to post this in case it is too late... We will present this in the ICLR Workshop on Sparsity in LLMs (SLLM)! We found that the representation dimension can dominate the model performance in the structured pruning 🤯
#ICLR2025 #LLM #sparsity
Reposted by Mingxue (Mercy) Xu
imperial-nlp.bsky.social
Excited to share our ICLR and NAACL papers! Please come and say hi, we're super friendly :)
April 22, 2025 at 6:42 PM
mercyxu.bsky.social
Slightly lazy but feel need to post this in case it is too late... We will present this in the ICLR Workshop on Sparsity in LLMs (SLLM)! We found that the representation dimension can dominate the model performance in the structured pruning 🤯
#ICLR2025 #LLM #sparsity
April 11, 2025 at 4:21 PM
Reposted by Mingxue (Mercy) Xu
lisaalaz.bsky.social
Do LLMs need rationales for learning from mistakes? 🤔
When LLMs learn from previous incorrect answers, they typically observe corrective feedback in the form of rationales explaining each mistake. In our new preprint, we find these rationales do not help, in fact they hurt performance!

🧵
February 13, 2025 at 3:38 PM
mercyxu.bsky.social
Happy New Year Everyone!
Here are the greetings from spring 🌸👇
January 1, 2025 at 10:27 AM
Reposted by Mingxue (Mercy) Xu
joestacey.bsky.social
Welcome to Bluesky to more of our NLP researchers at Imperial!! Looking forward to following everyone's work on here.

To follow us all click 'follow all' in the starter pack below

go.bsky.app/Bv5thAb
November 20, 2024 at 8:35 AM