Mirco Musolesi
@mircomusolesi.bsky.social
Professor of Computer Science. Machine Intelligence Lab, UCL AI Centre, Department of Computer Science, University College London.
Artificial Intelligence | Machine Learning | Computing | Books
https://www.mircomusolesi.org
Artificial Intelligence | Machine Learning | Computing | Books
https://www.mircomusolesi.org
Rightmove added the strapline “believe it” to its logo. The reference to what an estate agent tells you is clear (don’t).
November 11, 2025 at 8:01 AM
Rightmove added the strapline “believe it” to its logo. The reference to what an estate agent tells you is clear (don’t).
Reposted by Mirco Musolesi
![Comic. Someone is claiming to predict the exact date of a future earthquake. Should you listen? [flowchart: start] → NO (There are big earthquakes constantly, so if anyone ever *does* figure this out, it will be immediately obvious that their method works and then the world’s seismologists will not shut up about it. You won’t need this flowchart.)](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:cz73r7iyiqn26upot4jtjdhk/bafkreic7wdqg4w6qfevbqzzq4esd6237pojsnpwsrbb7gaxsxobqaiwazm@jpeg)
November 10, 2025 at 8:55 PM
This blogpost by Cal Newport is pretty good: "Forget Chatbots You Need a Notebook". calnewport.com/forget-chatb...
Forget Chatbots. You Need a Notebook. - Cal Newport
Back in 2012, as a young assistant professor, I traveled to Berkeley to attend a wedding. On the first morning after we arrived, my wife ... Read more
calnewport.com
November 10, 2025 at 9:11 PM
This blogpost by Cal Newport is pretty good: "Forget Chatbots You Need a Notebook". calnewport.com/forget-chatb...
More wonders of the natural world. Now some flowers of the plant in my office appear as if suspended in the void. This looks like a “technique” to invite pollinators. Or maybe it is a self-pollinating plant and these flowers contain seeds (?). 1/2
November 5, 2025 at 2:14 PM
More wonders of the natural world. Now some flowers of the plant in my office appear as if suspended in the void. This looks like a “technique” to invite pollinators. Or maybe it is a self-pollinating plant and these flowers contain seeds (?). 1/2
The Singularity is Not Near.
October 30, 2025 at 8:58 AM
The Singularity is Not Near.
Reposted by Mirco Musolesi
![Comic. [two connected spacecraft hovering in space above the Earth] Houston, the view is superb. We can see the continents spread out below us, right where they’ve been since the Earth formed. [caption] I still can’t believe we developed spaceflight before we figured out that the continents moved.](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:cz73r7iyiqn26upot4jtjdhk/bafkreicp2ka5asjgkmgfdfj33vnjb5bbvk3vnyao6ju5kipxcdc23pqasm@jpeg)
October 27, 2025 at 8:05 PM
Re the AWS outage, it’s quite cool that the BBC interviewed Ken Birman, who knows a thing or two about distributed systems. 1/2
October 21, 2025 at 7:18 AM
Re the AWS outage, it’s quite cool that the BBC interviewed Ken Birman, who knows a thing or two about distributed systems. 1/2
We received the ACM UbiComp 2025 10-Year Impact Award for our paper “Trajectories of Depression: Unobtrusive Monitoring of Depressive States by means of Smartphone Mobility Traces Analysis” co-authored with the great Luca Canzian. Paper here: www.mircomusolesi.org/papers/ubico... #ubicomp2025
October 16, 2025 at 9:02 AM
We received the ACM UbiComp 2025 10-Year Impact Award for our paper “Trajectories of Depression: Unobtrusive Monitoring of Depressive States by means of Smartphone Mobility Traces Analysis” co-authored with the great Luca Canzian. Paper here: www.mircomusolesi.org/papers/ubico... #ubicomp2025
New preprint with Charles Westphal and Stephen Hailes: "A Generalized Information Bottleneck Theory of Deep Learning". In this work, we introduce the Generalized Information Bottleneck framework, a synergy-based reformulation of the Information Bottleneck theory. arxiv.org/abs/2509.26327
October 15, 2025 at 11:40 AM
New preprint with Charles Westphal and Stephen Hailes: "A Generalized Information Bottleneck Theory of Deep Learning". In this work, we introduce the Generalized Information Bottleneck framework, a synergy-based reformulation of the Information Bottleneck theory. arxiv.org/abs/2509.26327
Lots of headlines claim graduates are more likely to be unemployed than non-graduates. Graduate unemployment panic makes good headlines, but the data says otherwise. Great analysis by @jburnmurdoch.ft.com. www.ft.com/content/ea9e...
.
.
What the graduate unemployment story gets wrong
People with a degree are faring better, not worse than their non-graduate counterparts
www.ft.com
October 10, 2025 at 12:54 PM
Lots of headlines claim graduates are more likely to be unemployed than non-graduates. Graduate unemployment panic makes good headlines, but the data says otherwise. Great analysis by @jburnmurdoch.ft.com. www.ft.com/content/ea9e...
.
.
New preprint: “Complexity-Driven Policy Optimization”. The paper discusses a novel complexity-driven policy optimisation solution for efficient and robust approximation in Reinforcement Learning. Essentially, entropy alone is not sufficient, we also need "structure".
📢 New Paper!
We replace the entropy bonus in PPO with a *complexity* bonus, encouraging structured and stochastic policies that are robust to different scaling factors and can work in environments with variable exploration needs.
Read more:
arxiv.org/abs/2509.20509
w/ @mircomusolesi.bsky.social
We replace the entropy bonus in PPO with a *complexity* bonus, encouraging structured and stochastic policies that are robust to different scaling factors and can work in environments with variable exploration needs.
Read more:
arxiv.org/abs/2509.20509
w/ @mircomusolesi.bsky.social
Complexity-Driven Policy Optimization
Policy gradient methods often balance exploitation and exploration via entropy maximization. However, maximizing entropy pushes the policy towards a uniform random distribution, which represents an un...
arxiv.org
October 8, 2025 at 12:49 PM
New preprint: “Complexity-Driven Policy Optimization”. The paper discusses a novel complexity-driven policy optimisation solution for efficient and robust approximation in Reinforcement Learning. Essentially, entropy alone is not sufficient, we also need "structure".
Received a copy of “The Library of Lost Maps” by my colleague James Cheshire at @uclgeography.bsky.social in the internal mail. Really beautiful (and very interesting) book. Thanks a lot James!
October 7, 2025 at 3:16 PM
Received a copy of “The Library of Lost Maps” by my colleague James Cheshire at @uclgeography.bsky.social in the internal mail. Really beautiful (and very interesting) book. Thanks a lot James!
For the geeks among you: just discovered the Apple Calculator app has a "Programmer" mode, complete with binary, hex, and related operations.
October 4, 2025 at 11:49 AM
For the geeks among you: just discovered the Apple Calculator app has a "Programmer" mode, complete with binary, hex, and related operations.
I was thinking about this some weeks ago. The Travelling Salesman Problem (finding the shortest path through a list of cities, visiting each only once), a classic in Computer Science/Maths, is becoming something of the past without actual salesmen on the roads. 1/2
In the 1980s and 1990s salesmen slogged up and down Britain’s motorways. Today that “road-warrior” lifestyle has disappeared. There are several reasons why
British men are driving less, and a culture is vanishing
Farewell to the road warriors
econ.st
October 1, 2025 at 9:30 PM
I was thinking about this some weeks ago. The Travelling Salesman Problem (finding the shortest path through a list of cities, visiting each only once), a classic in Computer Science/Maths, is becoming something of the past without actual salesmen on the roads. 1/2
Wonders of the natural world. I inherited an office cactus from a colleague who left. In a matter of days, out of nothing the cactus has developed a very long stem (with flowers).
September 22, 2025 at 8:35 AM
Wonders of the natural world. I inherited an office cactus from a colleague who left. In a matter of days, out of nothing the cactus has developed a very long stem (with flowers).
Today Charlie Westphal will present our paper "Feature Selection for Network Intrusion Detection" in the main Research Track of ACM KDD 2025 in Toronto.
Link to the paper: dl.acm.org/doi/pdf/10.1...
#KDD2025
Link to the paper: dl.acm.org/doi/pdf/10.1...
#KDD2025
August 6, 2025 at 12:14 AM
Today Charlie Westphal will present our paper "Feature Selection for Network Intrusion Detection" in the main Research Track of ACM KDD 2025 in Toronto.
Link to the paper: dl.acm.org/doi/pdf/10.1...
#KDD2025
Link to the paper: dl.acm.org/doi/pdf/10.1...
#KDD2025
Dream jobs and where to find them. linkedin.com/jobs/view/42...
June 19, 2025 at 11:25 AM
Dream jobs and where to find them. linkedin.com/jobs/view/42...
If you are attending #RLDM2025 in Dublin this week, do not miss the posters by Liza Tennant (liza-tennant.github.io) and Lorenz Wolf (profiles.ucl.ac.uk/90553-lorenz...) showcasing the work of our lab!
rldm.org
@rldmdublin2025.bsky.social
rldm.org
@rldmdublin2025.bsky.social
June 11, 2025 at 7:28 PM
If you are attending #RLDM2025 in Dublin this week, do not miss the posters by Liza Tennant (liza-tennant.github.io) and Lorenz Wolf (profiles.ucl.ac.uk/90553-lorenz...) showcasing the work of our lab!
rldm.org
@rldmdublin2025.bsky.social
rldm.org
@rldmdublin2025.bsky.social
Many posts about Apple announcements following WWDC25. I definitely like the glassy widgets. Less attention has been paid to the passing of Bill Atkinson, a real (personal) computer pioneer. This NYT obituary is quite good: www.nytimes.com/2025/06/07/t... 1/2
Bill Atkinson, Who Made Computers Easier to Use, Is Dead at 74
www.nytimes.com
June 10, 2025 at 12:36 PM
Many posts about Apple announcements following WWDC25. I definitely like the glassy widgets. Less attention has been paid to the passing of Bill Atkinson, a real (personal) computer pioneer. This NYT obituary is quite good: www.nytimes.com/2025/06/07/t... 1/2
8 days left to apply!
The second call for applications to the CDT in Cyber-Physical Risk is now open. I am offering two projects in the area of AI and cybersecurity. I would be happy to chat about this opportunity if you are interested.
www.ucl.ac.uk/security-cri...
Closing date: 15 June 2025.
www.ucl.ac.uk/security-cri...
Closing date: 15 June 2025.
June 7, 2025 at 11:50 AM
8 days left to apply!
The second call for applications to the CDT in Cyber-Physical Risk is now open. I am offering two projects in the area of AI and cybersecurity. I would be happy to chat about this opportunity if you are interested.
www.ucl.ac.uk/security-cri...
Closing date: 15 June 2025.
www.ucl.ac.uk/security-cri...
Closing date: 15 June 2025.
May 29, 2025 at 10:59 AM
The second call for applications to the CDT in Cyber-Physical Risk is now open. I am offering two projects in the area of AI and cybersecurity. I would be happy to chat about this opportunity if you are interested.
www.ucl.ac.uk/security-cri...
Closing date: 15 June 2025.
www.ucl.ac.uk/security-cri...
Closing date: 15 June 2025.
Also, presented in the Blue Sky Track, so this seems the right place to advertise it.
Today our paper with James Rudd-Jones and María Pérez-Ortiz "Multi-Agent Reinforcement Learning Simulation for Environmental Policy Synthesis" will be presented at the #AAMAS2025 Conference in Detroit.
Time: 2pm ET
Room: Richard
Link to the paper: arxiv.org/abs/2504.12777
@aamasconf.bsky.social
Time: 2pm ET
Room: Richard
Link to the paper: arxiv.org/abs/2504.12777
@aamasconf.bsky.social
May 21, 2025 at 6:31 PM
Also, presented in the Blue Sky Track, so this seems the right place to advertise it.
Today our paper with James Rudd-Jones and María Pérez-Ortiz "Multi-Agent Reinforcement Learning Simulation for Environmental Policy Synthesis" will be presented at the #AAMAS2025 Conference in Detroit.
Time: 2pm ET
Room: Richard
Link to the paper: arxiv.org/abs/2504.12777
@aamasconf.bsky.social
Time: 2pm ET
Room: Richard
Link to the paper: arxiv.org/abs/2504.12777
@aamasconf.bsky.social
May 21, 2025 at 6:24 PM
Today our paper with James Rudd-Jones and María Pérez-Ortiz "Multi-Agent Reinforcement Learning Simulation for Environmental Policy Synthesis" will be presented at the #AAMAS2025 Conference in Detroit.
Time: 2pm ET
Room: Richard
Link to the paper: arxiv.org/abs/2504.12777
@aamasconf.bsky.social
Time: 2pm ET
Room: Richard
Link to the paper: arxiv.org/abs/2504.12777
@aamasconf.bsky.social
Congratulations to Liza Tennant (liza-tennant.github.io) for passing her PhD viva today with a thesis on “Moral Alignment of Agentic AI Systems”! Well done Liza! And thanks to the examiners @jzleibo.bsky.social and John Shawe-Taylor for examining Liza’s dissertation.
May 15, 2025 at 7:54 PM
Congratulations to Liza Tennant (liza-tennant.github.io) for passing her PhD viva today with a thesis on “Moral Alignment of Agentic AI Systems”! Well done Liza! And thanks to the examiners @jzleibo.bsky.social and John Shawe-Taylor for examining Liza’s dissertation.
If you are attending #AISTAT2025, do not miss Charlie's presentation tomorrow.
Our paper "Partial Information Decomposition for Data Interpretability and Feature Selection" with Charlie Westphal and Steve Hailes will be presented at #AISTAT2025 on Sunday.
Session details: Spot 151 in Session 2 (Sun, May 4).
Link to the paper: openreview.net/attachment?i...
Session details: Spot 151 in Session 2 (Sun, May 4).
Link to the paper: openreview.net/attachment?i...
May 3, 2025 at 4:12 PM
If you are attending #AISTAT2025, do not miss Charlie's presentation tomorrow.