Eleonora Giunchiglia
@e-giunchiglia.bsky.social
Assistant Professor at Imperial College London | EEE Department and I-X.
Neuro-symbolic AI, Safe AI, Generative Models
Previously: Post-doc at TU Wien, DPhil at the University of Oxford.
Neuro-symbolic AI, Safe AI, Generative Models
Previously: Post-doc at TU Wien, DPhil at the University of Oxford.
In the paper, we also show that with just 1 labelled datapoint per concept, our prototypical NeSy model achieves the same number of symbolic optima as full dense supervision.
👉 Prototypes cut annotation cost without losing expressivity.
👉 Prototypes cut annotation cost without losing expressivity.
November 6, 2025 at 10:40 AM
In the paper, we also show that with just 1 labelled datapoint per concept, our prototypical NeSy model achieves the same number of symbolic optima as full dense supervision.
👉 Prototypes cut annotation cost without losing expressivity.
👉 Prototypes cut annotation cost without losing expressivity.
With just 2 labeled points, we can anchor each class to a single prototype—so the embedding updates reflect both similarity to the few labels and constraint satisfaction.
This helps in making the NeSy models #robust wrt the number of unsupervised datapoints!
This helps in making the NeSy models #robust wrt the number of unsupervised datapoints!
November 6, 2025 at 10:40 AM
With just 2 labeled points, we can anchor each class to a single prototype—so the embedding updates reflect both similarity to the few labels and constraint satisfaction.
This helps in making the NeSy models #robust wrt the number of unsupervised datapoints!
This helps in making the NeSy models #robust wrt the number of unsupervised datapoints!
🔍 Watch how the decision boundaries evolve!
This GIF shows PCA projections of the Semantic Loss model’s logits during training on MNIST-EvenOdd.
Colors = model predictions, points = true digit concepts
Above: standard semantic loss
Below: prototypical semantic loss
This GIF shows PCA projections of the Semantic Loss model’s logits during training on MNIST-EvenOdd.
Colors = model predictions, points = true digit concepts
Above: standard semantic loss
Below: prototypical semantic loss
November 6, 2025 at 10:40 AM
🔍 Watch how the decision boundaries evolve!
This GIF shows PCA projections of the Semantic Loss model’s logits during training on MNIST-EvenOdd.
Colors = model predictions, points = true digit concepts
Above: standard semantic loss
Below: prototypical semantic loss
This GIF shows PCA projections of the Semantic Loss model’s logits during training on MNIST-EvenOdd.
Colors = model predictions, points = true digit concepts
Above: standard semantic loss
Below: prototypical semantic loss
🤝 Collaborate with us to push the boundaries of neurosymbolic AI in scientific discovery.
🔗Link to the position: jobs.ac.uk/job/DPB378
#NeuroSymbolicAI #AI4Science #ChemAI #Postdoc #Hiring #AcademicJobs
🔗Link to the position: jobs.ac.uk/job/DPB378
#NeuroSymbolicAI #AI4Science #ChemAI #Postdoc #Hiring #AcademicJobs
Research Associate positions in Computational Chemistry, AI in Chemistry, and in Neurosymbolic Learning for Chemistry at Imperial College London
Apply now for the Research Associate positions in Computational Chemistry, AI in Chemistry, and in Neurosymbolic Learning for Chemistry role on jobs.ac.uk - the leading job board for higher education ...
jobs.ac.uk
November 4, 2025 at 6:23 PM
🤝 Collaborate with us to push the boundaries of neurosymbolic AI in scientific discovery.
🔗Link to the position: jobs.ac.uk/job/DPB378
#NeuroSymbolicAI #AI4Science #ChemAI #Postdoc #Hiring #AcademicJobs
🔗Link to the position: jobs.ac.uk/job/DPB378
#NeuroSymbolicAI #AI4Science #ChemAI #Postdoc #Hiring #AcademicJobs
If you made it this far, you're probably really into constraint-aware models 😄
Don’t miss the new paper by @nolovedeeplearning.bsky.social et al!
👉https://arxiv.org/abs/2503.19466
It proposes a probabilistic layer ensuring satisfaction of algebraic constraints over continuous variables—cool stuff!
Don’t miss the new paper by @nolovedeeplearning.bsky.social et al!
👉https://arxiv.org/abs/2503.19466
It proposes a probabilistic layer ensuring satisfaction of algebraic constraints over continuous variables—cool stuff!
April 23, 2025 at 9:47 AM
If you made it this far, you're probably really into constraint-aware models 😄
Don’t miss the new paper by @nolovedeeplearning.bsky.social et al!
👉https://arxiv.org/abs/2503.19466
It proposes a probabilistic layer ensuring satisfaction of algebraic constraints over continuous variables—cool stuff!
Don’t miss the new paper by @nolovedeeplearning.bsky.social et al!
👉https://arxiv.org/abs/2503.19466
It proposes a probabilistic layer ensuring satisfaction of algebraic constraints over continuous variables—cool stuff!
🗓️ 𝐂𝐮𝐫𝐢𝐨𝐮𝐬? Come chat with us at 𝐇𝐚𝐥𝐥 𝟑 + 𝐇𝐚𝐥𝐥 𝟐𝐁, 𝐏𝐨𝐬𝐭𝐞𝐫 #𝟏𝟕𝟐 on 𝐀𝐩𝐫𝐢𝐥 𝟐𝟔𝐭𝐡!
Link to paper: arxiv.org/pdf/2502.18237
Link to paper: arxiv.org/pdf/2502.18237
arxiv.org
April 23, 2025 at 9:47 AM
🗓️ 𝐂𝐮𝐫𝐢𝐨𝐮𝐬? Come chat with us at 𝐇𝐚𝐥𝐥 𝟑 + 𝐇𝐚𝐥𝐥 𝟐𝐁, 𝐏𝐨𝐬𝐭𝐞𝐫 #𝟏𝟕𝟐 on 𝐀𝐩𝐫𝐢𝐥 𝟐𝟔𝐭𝐡!
Link to paper: arxiv.org/pdf/2502.18237
Link to paper: arxiv.org/pdf/2502.18237
🔍
We applied this to tabular data generation, showing our models not only satisfy the constraints, but also produce more realistic datapoints and 𝐨𝐮𝐭𝐩𝐞𝐫𝐟𝐨𝐫𝐦 𝐮𝐧𝐜𝐨𝐧𝐬𝐭𝐫𝐚𝐢𝐧𝐞𝐝 𝐛𝐚𝐬𝐞𝐥𝐢𝐧𝐞𝐬.
We applied this to tabular data generation, showing our models not only satisfy the constraints, but also produce more realistic datapoints and 𝐨𝐮𝐭𝐩𝐞𝐫𝐟𝐨𝐫𝐦 𝐮𝐧𝐜𝐨𝐧𝐬𝐭𝐫𝐚𝐢𝐧𝐞𝐝 𝐛𝐚𝐬𝐞𝐥𝐢𝐧𝐞𝐬.
April 23, 2025 at 9:47 AM
🔍
We applied this to tabular data generation, showing our models not only satisfy the constraints, but also produce more realistic datapoints and 𝐨𝐮𝐭𝐩𝐞𝐫𝐟𝐨𝐫𝐦 𝐮𝐧𝐜𝐨𝐧𝐬𝐭𝐫𝐚𝐢𝐧𝐞𝐝 𝐛𝐚𝐬𝐞𝐥𝐢𝐧𝐞𝐬.
We applied this to tabular data generation, showing our models not only satisfy the constraints, but also produce more realistic datapoints and 𝐨𝐮𝐭𝐩𝐞𝐫𝐟𝐨𝐫𝐦 𝐮𝐧𝐜𝐨𝐧𝐬𝐭𝐫𝐚𝐢𝐧𝐞𝐝 𝐛𝐚𝐬𝐞𝐥𝐢𝐧𝐞𝐬.
📩 Interested? Apply now: e.giunchiglia@imperial.ac.uk
📌 Use [PhD Application] in the email subject
@imperial-ix.bsky.social @imperialeee.bsky.social @imperialcollegeldn.bsky.social @nesyconf.org
[3/3]
📌 Use [PhD Application] in the email subject
@imperial-ix.bsky.social @imperialeee.bsky.social @imperialcollegeldn.bsky.social @nesyconf.org
[3/3]
February 5, 2025 at 1:53 PM
📩 Interested? Apply now: e.giunchiglia@imperial.ac.uk
📌 Use [PhD Application] in the email subject
@imperial-ix.bsky.social @imperialeee.bsky.social @imperialcollegeldn.bsky.social @nesyconf.org
[3/3]
📌 Use [PhD Application] in the email subject
@imperial-ix.bsky.social @imperialeee.bsky.social @imperialcollegeldn.bsky.social @nesyconf.org
[3/3]
📢 What’s included?
✅ Full scholarship for UK/EU citizens with (pre-)settled status
✅ Industry collaboration: 3-month internship with our partner company
✅ Be part of a world-class research environment 🌍
[2/3]
✅ Full scholarship for UK/EU citizens with (pre-)settled status
✅ Industry collaboration: 3-month internship with our partner company
✅ Be part of a world-class research environment 🌍
[2/3]
February 5, 2025 at 1:53 PM
📢 What’s included?
✅ Full scholarship for UK/EU citizens with (pre-)settled status
✅ Industry collaboration: 3-month internship with our partner company
✅ Be part of a world-class research environment 🌍
[2/3]
✅ Full scholarship for UK/EU citizens with (pre-)settled status
✅ Industry collaboration: 3-month internship with our partner company
✅ Be part of a world-class research environment 🌍
[2/3]