Andrea Pugnana
@andrepugni
Followers
184
Following
823
Media
7
Statuses
168
RTD-A @UniTrento_DISI. My own view. He/him.
Sarzana
Joined March 2018
RT @ragionedistato: C'è stato almeno un attimo nella vita di tutti nel quale abbiamo pensato che Saponara fosse il miglior trequartista del….
0
29
0
RT @random_walker: Some aspects of AI discourse seem to come from a different planet, oblivious to basic realities on Earth. AI for science….
0
74
0
RT @steveazzolin: 🧐What are the properties of self-explanations in GNNs? What can we expect from them?. We investigate this in our #ICML25….
0
4
0
RT @ruggieris: Few days left for.Call for Applications: Italian National PhD in Artificial Intelligence – AI & Society (2025-2028) .🎓 𝟒𝟒 𝐟….
0
6
0
RT @steveazzolin: This is an issue on multiple levels, and authors using those "shortcuts"👀 are equally responsible for this unethical beha….
0
2
0
RT @josephimperial_: NeurIPS D&B track in a nutshell:. (1) An LLM-generated benchmark dataset.(2) used to test performance of LLMs.(3) eval….
0
47
0
RT @ruggieris: Call for Applications: Italian National PhD in Artificial Intelligence – AI & Society (2025-2028).🔗 Apply here: https://t.co….
phd-ai-society.di.unipi.it
Interested in a multi-disciplinary Ph.D. program oriented at cutting-edge fundamental and applied research in Human-centered Artificial Intelligence and its impacts…Leggi tutto...
0
17
0
RT @giovanni_detoni: Just landed in Athens 🇬🇷 for #FAccT25! I’ll be presenting our work on the fragility of causal recourse over time (http….
0
3
0
RT @ema_marconato: 🧵Why are linear properties so ubiquitous in LLM representations?. We explore this question through the lens of 𝗶𝗱𝗲𝗻𝘁𝗶𝗳𝗶𝗮….
0
61
0
RT @ecmaEditors: Public funds to Italian firms in disadvantaged areas (ex. Law 488/92) permanently increased employment, but allocation mat….
0
87
0
RT @r_massidda: 🔥 Five days left to submit your work to our causality workshop at #UAI2025!. 🇧🇷 You bring the paper, we bring world-class k….
0
6
0
RT @mic_caprio: If you're about to finish your PhD and considering a postdoc, there are two wonderful opportunities to work with us on Unce….
marie-sklodowska-curie-actions.ec.europa.eu
The information provided on this page is a summary of the main rules and requirements for Postdoctoral Fellowships (PFs) and who can apply for them.
0
4
0
RT @ema_marconato: Now in Thailand to present our paper at #AISTATS2025 🇹🇭🌴. 📍Today at 3:00-6:00 pm, poster number 118!. More details here:….
openreview.net
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”...
0
4
0
👀 Want to dive deeper? Curious how ML + humans really perform together?.📍Come find us at our poster: Hall A-E 160, May 3rd. 5/5.
0
0
3
🔍 We define wo scenarios:.1️⃣ Both human and ML predictions for deferred cases? We can estimate individual & aggregate causal effects. 2️⃣ Only human predictions for deferred cases? We can use Regression Discontinuity Design for local causal effects. 4/5.
1
0
3
In our work, we bring causal inference to the arena. Using the potential outcomes framework, we ask: What’s the actual impact of deferring to humans on system performance? 🎯. 3/5.
1
0
2
🧠🤖 Deferring systems let ML models pass the mic to humans when they are better at predicting. But what is the actual impact on predictive performance of such systems? Surprisingly, such a question is still overlooked. 2/5.
1
0
2
On my way to Mai Khao 🇹🇭🏝️ for #AISTATS2025, where I will present A Causal Framework for Evaluating Deferring Systems, a joint work with Filippo Palomba, @cc_jalvarez and @ruggieris. 1/5.
1
3
14
RT @diegocalanzone: #ICLR 2025 is starting tomorrow! Come have a chat if you are interested in drug discovery, reasoning, agents and logic….
0
2
0