Emanuele Marconato
@ema-ridopoco.bsky.social
Post-doc @ University of Trento. I did my PhD @ University of Trento and the University of Pisa. I like #concepts, #symbols, and #representations, but I still don't know what they are. 📍 Trento, Italy 🧵 #identifiability, #shortcuts, #interpretability
See you in San Diego 😉🏜️🏄♂️
Beatrix M. G. Nielsen@beatrixmgn.bsky.social · 10mo agoI am happy to announce that our article "When Does Closeness in Distribution Imply Representational Similarity? An Identifiability Perspective" has been accepted at NeurIPS 2025! 🎉 arxiv.org/abs/2506.037... Details below 👇
🧵Why are linear properties so ubiquitous in LLM representations? We explore this question through the lens of 𝗶𝗱𝗲𝗻𝘁𝗶𝗳𝗶𝗮𝗯𝗶𝗹𝗶𝘁𝘆: “All or None: Identifiable Linear Properties of Next-token Predictors in Language Modeling” Published at #AISTATS2025🌴 1/9
Now in Thailand to present our paper at #AISTATS2025 🇹🇭🌴 📍Today at 3:00-6:00 pm, poster number 118! More details here: openreview.net/forum?id=XCm...
All or None: Identifiable Linear Properties of Next-Token...
We analyze identifiability as a possible explanation for the ubiquity of linear properties across language models, such as the vector difference between the representations of “easy” and “easiest”...
openreview.net
Only yesterday I discovered that my PhD thesis has been made public to everyone 😅 I worked three years on "Learning concepts" and I tried to spot the connection between #concepts, #symbols, and #representations, and how they're used in ML today 👾🪄 etd.adm.unipi.it/t/etd-012620...
Tesi etd-01262025-170550
etd.adm.unipi.it
Hey hey! We have an accepted paper at #AISTATS2025!! Time to prepare for Thailand 🪷🏖️🌴🐒 Huge thanks to my coauthors Luigi Gresele, Sebastian Weichwald, and @seblachap.bsky.social for all the joint effort! More details soon 👇 arxiv.org/abs/2410.235...
Don't miss the chance to learn more about our new #benchmark suite @ #NeurIPS2024 📊 New benchmarks to test concept quality learned by all kinds of models: Neural, NeSy, Concept-based, and Foundation models. 🤔 All models learn to solve the task but, beware, do they learn concepts?? Spoiler: 😱
Samuele Bortolotti@samubortolotti.bsky.social · 2y ago📣 Does your model learn high-quality #concepts, or does it learn a #shortcut? Test it with our #NeurIPS2024 dataset & benchmark track paper! rsbench: A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcuts What's the deal with rsbench? 🧵
📣 Does your model learn high-quality #concepts, or does it learn a #shortcut? Test it with our #NeurIPS2024 dataset & benchmark track paper! rsbench: A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcuts What's the deal with rsbench? 🧵
The #NeurIPS experience is about to start! ✈ Drop me a line if you want to chat about #neurosymbolic reasoning #shortcuts, human-interpretable machine #concepts, logically-consistent #LLMs, or human-in-the-➰ #XAI! See you in Vancouver!
For those attending #NeurIPS2024 go to UNIREPS @unireps.bsky.social workshop to know more about representations similarity. Nice work led by @beatrixmgn.bsky.social 🌟
Andrea Dittadi@andreadittadi.bsky.social · 2y agoWhy do NNs often learn similar representations? Existing identifiability results offer theoretical insights, but applying them in practice poses challenges. We’ll present our new work exploring these challenges next week at @unireps #NeurIPS2024 🇨🇦🎉 openreview.net/pdf?id=SQKUZSieVg 1/
🚨 Interpretable AI often means sacrificing accuracy—but what if we could have both? Most interpretable AI models, like Concept Bottleneck Models, force us to trade accuracy for interpretability. But not anymore, due to Concept-Based Memory Reasoner (CMR)! #NeurIPS2024 (1/7)
