Ne Luo

PhD student @UniMelb | MSc @EdinburghNLP | interested in #NLP and #RL

[Ne Luo @neluo19]

@hapyresearchers My plan: Undergrad -> Engineer -> MSc -> PhD -> Barista

[Pasquale Minervini @PMinervini]

The amazing folks at @EdinburghNLP will be presenting a few papers at ACL 2025 (@aclmeeting); if you're in Vienna, touch base with them! Here are the papers in the main track 🧵

[Ne Luo @neluo19]

@miniapeur Remind myself that happiness is a choice.

[Aryo Pradipta Gema @aryopg]

New Anthropic Research: “Inverse Scaling in Test-Time Compute”

We found cases where longer reasoning leads to lower accuracy.
Our findings suggest that naïve scaling of test-time compute may inadvertently reinforce problematic reasoning patterns.

🧵

[Alessio Devoto @devoto_alessio]

🏆 Our @nvidia KV Cache Compression Leaderboard is now live!

Compare state-of-the-art compression methods side-by-side with KVPress. See which techniques are leading in efficiency and performance. 🥇
https://t.co/kP9fdEG5JZ

[Ne Luo @neluo19]

@miniapeur Steam?

[Pasquale Minervini @PMinervini]

Please catch up with Ne (@neluo19) and the others (modulo visa issues) at NAACL!

[Ne Luo @neluo19]

Huge thanks to my amazing supervisor @PMinervini and collaborators @aryopg @zodiacJRH @EmilevanKrieken @pietro_lesci!!

[Ne Luo @neluo19]

Hi! I will be attending #NAACL2025 and presenting our paper on self-training for tool-use today, an extended work of my MSc dissertation at @EdinburghNLP, supervised by @PMinervini.

Time: 14:00-15:30
Location: Hall 3

Let’s chat and connect!😊

[Yu Zhao @yuzhaouoe]

NAACL 2025 Oral Presentation💥

Our work about using Sparse AutoEncoder to resolve knowledge conflict will present on 30 Apr 11:30–11:45 AM • Ballroom C

Thank Hongru for presenting our work!!!

[Ne Luo @neluo19]

@DBahdanau LOL

[Ne Luo @neluo19]

@ZhiruoW @AkariAsai @FariaHuqOaishi (Will your cat be attending the poster session as well?😻)

[Ne Luo @neluo19]

@cong_ml @shengranhu @jeffclune Super cool work!

[Ne Luo @neluo19]

Grateful to be part of this! I'll be presenting our paper "Self-Training Large Language Models for Tool-Use Without Demonstrations" at #NAACL2025! Also, I am currently seeking PhD opportunities. Please feel free to reach out if you're recruiting or know of any openings! :)

[Pasquale Minervini @PMinervini]

My amazing collaborators will present several works at ICLR and NAACL later this month -- please catch up with them if you're attending! I tried to summarise our recent work in a blog post: https://t.co/wF8dqldSqv

[Richard Sutton @RichardSSutton]

David Silver really hits it out of the park in this podcast. The paper "Welcome to the Era of Experience" is here: https://t.co/Y6m4jLRjnh.

[Peyman Milanfar @docmilanfar]

Researchers’ Credo

[Ne Luo @neluo19]

@aryopg @AnthropicAI Congrats Aryo!!!

[elvis @omarsar0]

This is an excellent survey of post-training methods for LLMs

[Edward Hughes @edwardfhughes]

Agreed. Open-endedness is not just scaled-up objective optimisation. It is non-objective search. And it’s crucial for reaching ASI.

[Yu Zhao @yuzhaouoe]

We find a single biased direction encodes a KV Cache selection mechanism in Self-Attention -- Key vector with a strong component in this direction results in this Key-Value pair being ignored by Query🚀🚀🚀