andreas_madsen Profile Banner
Andreas Madsen Profile
Andreas Madsen

@andreas_madsen

Followers
6K
Following
1K
Media
121
Statuses
2K

Ph.D. in NLP Interpretability from Mila. Previously, independent researcher + freelancer in ML and Node.js core developer.

Montreal, Canada
Joined December 2010
Don't wanna be here? Send us removal request.
@andreas_madsen
Andreas Madsen
1 year
Spotlight award at ICML 2024. Introducing a new direction for interpretability: Faithfulness Measurable Models. 2x-5x better explanations, more accurate faithfulness metrics, no cost, and optimal explanations. Paper: https://t.co/UU5aTvaTsu. Hall C 4-9, 24 Jul (11:30 - 13:00).
11
29
152
@andreas_madsen
Andreas Madsen
6 months
Python; calling it "t-string", is just troublesome when I need to lookup documentation at work.
0
0
3
@asalam_91
Aya Abdelsalam Ismail
7 months
Interpretable Lobsters at #ICLR2025 🦞 🦞 Come by poster #504!
2
7
96
@sarahookr
Sara Hooker
7 months
Very special being back in Montreal ✨ Huge thank you to @hugo_larochelle @apsarathchandar Marc-Alexandre Cote for bringing us together for MILA techaide.
1
13
106
@kayo_yin
Kayo Yin
7 months
hearing “I’ve never really thought about signed language before but your talk made me want to work on it” is the biggest compliment!! maybe my talks are all recruitment pitches disguised as research talks
1
2
44
@apsarathchandar
Sarath Chandar
8 months
In my lab, we have not one but four open postdoc positions! These positions cover developing foundation models for text, proteins, small molecules, genomic data, time series data, and astrophysics data! If you have strong research expertise and a PhD in LLMs and Foundation
3
34
117
@1littlecoder
1LittleCoder💻
9 months
A new BERT baby! If you are still using the huge RoBERTa or DeBERTa for your NLP tasks, here's NeoBERT!
2
12
79
@Mila_Quebec
Mila - Institut québécois d'IA
8 months
Congratuations to Lola (@lo_LB_La) and Sarath (@apsarathchandar) Read their blog post: https://t.co/v3v6bjteuN
@apsarathchandar
Sarath Chandar
9 months
2025 BERT is NeoBERT! We have fully pre-trained a next-generation encoder for 2.1T tokens with the latest advances in data, training, and architecture. This is a heroic effort from my PhD student @lo_LB_La in collaboration with @qfournier2 and Mariam El Mezouar (1/n)
0
5
27
@apsarathchandar
Sarath Chandar
9 months
What's the foundational model for generative chemistry? Our work, BindGPT, is a good candidate, and it will be presented at #AAAI2025 today! We built a simple transformer language model that beats diffusion models by just generating 3D molecules as text! Led by @artemZholus 1/n
2
8
29
@andreas_madsen
Andreas Madsen
9 months
Also thanks to @apsarathchandar and @sivareddyg for supporting me during my Ph.D., which helped me get this far! I would highly recommend them if you are looking for a Ph.D. supervisor.
0
0
3
@andreas_madsen
Andreas Madsen
9 months
Positions: * Full-stack * Research Engineer * Research Scientist * Systems Infrastructure Engineer * Research intern Feel free to reach out but chances are I will see your application if you apply online. I will post details on my internship later, but there are more openings.
1
0
1
@andreas_madsen
Andreas Madsen
9 months
Excited to finally announce that I have joined @guidelabsai. We are building LLMs from scratch designed to be interpretable. Many have asked what I'm doing after my Ph.D., so great to finally get it out. We have a lot of open positions, from engineering or scientist to intern.
2
3
29
@andreas_madsen
Andreas Madsen
10 months
This is very sad news. @FelixHill84 reached out to me during my time as an independent researcher because he wanted to collaborate with me on some ideas. This was the first time anyone well-known had ever wanted to work with me, so I was deeply appreciative. Felix was always
@douwekiela
Douwe Kiela
11 months
I’m really sad that my dear friend @FelixHill84 is no longer with us. He had many friends and colleagues all over the world - to try to ensure we reach them, his family have asked to share this webpage for the celebration of his life: https://t.co/1QoyHmAD3p
0
2
43
@andreas_madsen
Andreas Madsen
1 year
All investigations of faithfulness show that explanations' faithfulness is by default model and task-dependent. However, this is not the case when using FMMs. Thus, presenting a new paradigm for how to provide and ensure faithful explanations.
0
0
6
@andreas_madsen
Andreas Madsen
1 year
FMMs are when models are designed such that measuring faithfulness is cheap and precise, which makes it possible to optimize explanations toward maximum faithfulness.
1
0
8
@andreas_madsen
Andreas Madsen
1 year
Self-explanations are when LLMs explain themselves. Current models are not capable of this, but we suggest how that could be changed.
1
0
3
@andreas_madsen
Andreas Madsen
1 year
We ask the question: How to provide and ensure faithful explanations for general-purpose NLP models? The main thesis is that we should develop new paradigms in interpretability. The two new paradigms explored are faithfulness measurable models (FMMs) and self-explanations.
1
0
4
@andreas_madsen
Andreas Madsen
1 year
The full thesis is available at https://t.co/8MNLgtheST. Thanks to @sivareddyg and @apsarathchandar for supervising me throughout all these years. It's been a great journey and I'm very grateful for their support.
1
1
13
@andreas_madsen
Andreas Madsen
1 year
I’m thrilled to share that I’ve finished my Ph.D. at @Mila_Quebec. For the last 4.5 years, I have worked on creating new faithfulness-centric paradigms for NLP Interpretability. Read my vision for the future of interpretability in our newposition paper:
Tweet card summary image
arxiv.org
Interpretability is the study of explaining models in understandable terms to humans. At present, interpretability is divided into two paradigms: the intrinsic paradigm, which believes that only...
25
41
397
@andreas_madsen
Andreas Madsen
1 year
I would highly recommend this lab! Consider joining if you are interested in NLP.
@sivareddyg
Siva Reddy
1 year
I have multiple vacancies for PhD and Masters students at @Mila_Quebec @McGill_NLP in NLP/ML focusing on representation learning, reasoning, multimodality and alignment. Deadline for applications is Dec 1st. More details:
0
0
7