Matthew Kowal @ICML 🛩️🇨🇦💻
@MatthewKowal9
Followers
436
Following
6K
Media
42
Statuses
784
Research Resident @FARAIResearch / PhD @YorkUniversity @VectorInst / Previously @UbisoftLaForge @ToyotaResearch @_NextAI / AI Safety + Interpretability
Toronto, Canada
Joined March 2019
🧑🍳🍴On the concept menu for tonight: You have a choice of main course between 4413 (🍝) or 4538 (🍕), paired with 2587 (🍷), followed by a delicious dessert choice between 4183 (🍨) or 4893 (🍰).
🌌🛰️🔭Want to explore universal visual features? Check out our interactive demo of concepts learned from our #ICML2025 paper "Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment". Come see our poster at 4pm on Tuesday in East Exhibition hall A-B, E-1208!
0
4
15
RT @anna_hedstroem: Couldn’t be more excited to share our latest paper — accepted to ICML 2025 @icmlconf — with JP Morgan AI Research. It….
0
4
0
RT @EdTurner42: 1/8: The Emergent Misalignment paper showed LLMs trained on insecure code then want to enslave humanity. ?!. We're releasi….
0
47
0
RT @s_scardapane: *Universal Sparse Autoencoders*.by @HThasarathan @Napoolar @MatthewKowal9 @CSProfKGD . They train a shared SAE latent spa….
0
38
0
RT @EkdeepL: 🚨 New paper alert!. Linear representation hypothesis (LRH) argues concepts are encoded as **sparse sum of orthogonal direction….
0
63
0
RT @farairesearch: 🤔 Can lie detectors make AI more honest? Or will they become sneakier liars?. We tested what happens when you add decept….
0
8
0
RT @soniajoseph_: Our paper Prisma: An Open Source Toolkit for Mechanistic Interpretability in Vision and Video received an Oral at the Mec….
0
30
0
RT @farairesearch: “We purposely build or discover situations where models might be behaving in misaligned ways”. @EvanHub discusses stress….
0
152
0
RT @livgorton: if anyone is preparing for ML interviews (or is like me and just likes to essentially do interview-like Qs for fun lol), wou….
0
134
0
RT @ARGleave: My colleague @irobotmckenzie spent six hours red-teaming Claude 4 Opus, and easily bypassed safeguards designed to block WMD….
0
136
0
RT @NeelNanda5: Please note: The first sentence of this article is false. As we tried to clearly state in the title of the linked post, we….
0
11
0
RT @NeelNanda5: AI Control - the study of how to safely monitor and use pre-superintelligence AIs even if they're misaligned - seems very i….
0
8
0
RT @CSProfKGD: Accepted at #ICML2025! Check out the preprint. Shoutout to the group for an AMAZING research journey @HThasarathan @Julian….
0
12
0
RT @CSProfKGD: You think your network is learning? It might be "cheating". Some of our work digging into this:. 🔹Position, Padding and Pr….
0
5
0
RT @rgilman33: SDXL-turbo isn't given positional information—so it makes its own. You can see the positional grid forming in the first fe….
0
68
0
RT @farairesearch: 🤖 Model-free agents can internally plan!. Sokoban agents develop bidirectional search planning! .🔬 We probe for planning….
0
3
0
RT @kayembruno: How do you identify training data responsible for an image generated by your diffusion model? How could you quantify how mu….
0
22
0
RT @NeelNanda5: Very strongly agreed. Thanks for writing the post and saving me the need to! I think this is highly underrated in the mech….
0
4
0