MLIA ISIR
@mlia-isir.bsky.social
MLIA research team at CNRS/ISIR lab in Sorbonne University @sorbonne-universite.fr
https://www.isir.upmc.fr/equipes/mlia/
https://www.isir.upmc.fr/equipes/mlia/
📣 PhD defense announcement ! 📣
Raphaël Mouravieff will defend his PhD titled "Deep Learning Approaches for Improving Generalization in Table Question-Answering."
📆 Monday, December 1st at 10:00 AM
📍 Room RC27 Atrium, 4 Place Jussieu, 75005 Paris
🖥️ A link will be provided to follow remotely
Raphaël Mouravieff will defend his PhD titled "Deep Learning Approaches for Improving Generalization in Table Question-Answering."
📆 Monday, December 1st at 10:00 AM
📍 Room RC27 Atrium, 4 Place Jussieu, 75005 Paris
🖥️ A link will be provided to follow remotely
November 29, 2025 at 4:58 PM
📣 PhD defense announcement ! 📣
Raphaël Mouravieff will defend his PhD titled "Deep Learning Approaches for Improving Generalization in Table Question-Answering."
📆 Monday, December 1st at 10:00 AM
📍 Room RC27 Atrium, 4 Place Jussieu, 75005 Paris
🖥️ A link will be provided to follow remotely
Raphaël Mouravieff will defend his PhD titled "Deep Learning Approaches for Improving Generalization in Table Question-Answering."
📆 Monday, December 1st at 10:00 AM
📍 Room RC27 Atrium, 4 Place Jussieu, 75005 Paris
🖥️ A link will be provided to follow remotely
➡️ JAFAR: Jack-up Any Feature at Any Resolution from Paul Couairon, Loïck Chambon, Louis Serrano, Jean-Emmanuel HAUGEARD, Matthieu Cord, Nicolas Thome in collaboration with Valeo.
📑 arxiv.org/abs/2506.11136
🖥️ github.com/PaulCouairon...
📑 arxiv.org/abs/2506.11136
🖥️ github.com/PaulCouairon...
November 25, 2025 at 8:57 AM
➡️ JAFAR: Jack-up Any Feature at Any Resolution from Paul Couairon, Loïck Chambon, Louis Serrano, Jean-Emmanuel HAUGEARD, Matthieu Cord, Nicolas Thome in collaboration with Valeo.
📑 arxiv.org/abs/2506.11136
🖥️ github.com/PaulCouairon...
📑 arxiv.org/abs/2506.11136
🖥️ github.com/PaulCouairon...
➡️ Learning to Steer: Input-dependent Steering for Multimodal LLMs from Jayneel Parekh, pegah khayatan, Mustafa Shukor, arnaud dapogny, Alasdair Newson, @matthieucord.bsky.social, in collaboration with Valeo.
📑 arxiv.org/pdf/2508.12815
🖥️ github.com/jayneelparek...
📑 arxiv.org/pdf/2508.12815
🖥️ github.com/jayneelparek...
November 24, 2025 at 6:32 PM
➡️ Learning to Steer: Input-dependent Steering for Multimodal LLMs from Jayneel Parekh, pegah khayatan, Mustafa Shukor, arnaud dapogny, Alasdair Newson, @matthieucord.bsky.social, in collaboration with Valeo.
📑 arxiv.org/pdf/2508.12815
🖥️ github.com/jayneelparek...
📑 arxiv.org/pdf/2508.12815
🖥️ github.com/jayneelparek...
➡️ CLIPTTA: Robust Contrastive Vision-Language Test-Time Adaptation from Marc Lafon, Gustavo Vargas Hakim, Clément Rambour, Christian Desrosiers, Nicolas Thome in collaboration with Conservatoire National des Arts et Métiers and École de technologie supérieure (ÉTS).
📑 arxiv.org/pdf/2507.14312
📑 arxiv.org/pdf/2507.14312
November 24, 2025 at 6:32 PM
➡️ CLIPTTA: Robust Contrastive Vision-Language Test-Time Adaptation from Marc Lafon, Gustavo Vargas Hakim, Clément Rambour, Christian Desrosiers, Nicolas Thome in collaboration with Conservatoire National des Arts et Métiers and École de technologie supérieure (ÉTS).
📑 arxiv.org/pdf/2507.14312
📑 arxiv.org/pdf/2507.14312
➡️ ENMA: Tokenwise Autoregression for Generative Neural PDE Operators. from Armand Kassaï Koupaï, Lise Le Boudec, Louis Serrano and patrick gallinari, in collaboration with Criteo. This work was accepted as a ✨Spotlight paper! ✨
📑 arxiv.org/abs/2506.06158
🌐 enma-pde.github.io
📑 arxiv.org/abs/2506.06158
🌐 enma-pde.github.io
November 24, 2025 at 6:32 PM
➡️ ENMA: Tokenwise Autoregression for Generative Neural PDE Operators. from Armand Kassaï Koupaï, Lise Le Boudec, Louis Serrano and patrick gallinari, in collaboration with Criteo. This work was accepted as a ✨Spotlight paper! ✨
📑 arxiv.org/abs/2506.06158
🌐 enma-pde.github.io
📑 arxiv.org/abs/2506.06158
🌐 enma-pde.github.io
The team meeting of the week was presented by Alexandre Vérine, from PSL, about "Quality and Diversity in generative models through the lens of f-divergences."
Thanks a lot for this interesting talk!
Thanks a lot for this interesting talk!
November 24, 2025 at 6:13 PM
The team meeting of the week was presented by Alexandre Vérine, from PSL, about "Quality and Diversity in generative models through the lens of f-divergences."
Thanks a lot for this interesting talk!
Thanks a lot for this interesting talk!
Great time at Suzhou for the EMNLP conference 🇨🇳
Thanks everyone for the great presentations and talks!
Thanks everyone for the great presentations and talks!
November 18, 2025 at 10:40 AM
Great time at Suzhou for the EMNLP conference 🇨🇳
Thanks everyone for the great presentations and talks!
Thanks everyone for the great presentations and talks!
🎉 PhD defense announcement!
Florian Le Bronnec will defend his PhD titled "Reliability of Generative Language Models: Efficiency, Faithfulness, and Coverage"! 👨🎓
🗓️When? Wed, November 26th, 14:00
📍Where? Amyot Amphitheater, PSL, 3 Rue Amyot, Paris.
Looking forward to seeing you there!
Abstract ⬇️
Florian Le Bronnec will defend his PhD titled "Reliability of Generative Language Models: Efficiency, Faithfulness, and Coverage"! 👨🎓
🗓️When? Wed, November 26th, 14:00
📍Where? Amyot Amphitheater, PSL, 3 Rue Amyot, Paris.
Looking forward to seeing you there!
Abstract ⬇️
November 7, 2025 at 10:24 AM
🎉 PhD defense announcement!
Florian Le Bronnec will defend his PhD titled "Reliability of Generative Language Models: Efficiency, Faithfulness, and Coverage"! 👨🎓
🗓️When? Wed, November 26th, 14:00
📍Where? Amyot Amphitheater, PSL, 3 Rue Amyot, Paris.
Looking forward to seeing you there!
Abstract ⬇️
Florian Le Bronnec will defend his PhD titled "Reliability of Generative Language Models: Efficiency, Faithfulness, and Coverage"! 👨🎓
🗓️When? Wed, November 26th, 14:00
📍Where? Amyot Amphitheater, PSL, 3 Rue Amyot, Paris.
Looking forward to seeing you there!
Abstract ⬇️
November 4, 2025 at 12:59 PM
🗒️ Yesterday, Ben Kabongo led the team meeting with his presentation "MemRec: Memory Network for Explainable Recommendation". Thanks for the interesting talk!
November 4, 2025 at 9:56 AM
🗒️ Yesterday, Ben Kabongo led the team meeting with his presentation "MemRec: Memory Network for Explainable Recommendation". Thanks for the interesting talk!
Accepted to a Workshop (2/2):
"On the Representations of Entities in Auto-regressive Large Language Models", accepted to the BlackBoxNLP Workshop, from @victormorand.bsky.social, Josiane Mothe & Benjamin Piwowarski
🎤 Nov 9th, 2025
Arxiv: arxiv.org/abs/2510.09421
Code: github.com/VictorMorand...
"On the Representations of Entities in Auto-regressive Large Language Models", accepted to the BlackBoxNLP Workshop, from @victormorand.bsky.social, Josiane Mothe & Benjamin Piwowarski
🎤 Nov 9th, 2025
Arxiv: arxiv.org/abs/2510.09421
Code: github.com/VictorMorand...
October 28, 2025 at 8:57 AM
Accepted to a Workshop (2/2):
"On the Representations of Entities in Auto-regressive Large Language Models", accepted to the BlackBoxNLP Workshop, from @victormorand.bsky.social, Josiane Mothe & Benjamin Piwowarski
🎤 Nov 9th, 2025
Arxiv: arxiv.org/abs/2510.09421
Code: github.com/VictorMorand...
"On the Representations of Entities in Auto-regressive Large Language Models", accepted to the BlackBoxNLP Workshop, from @victormorand.bsky.social, Josiane Mothe & Benjamin Piwowarski
🎤 Nov 9th, 2025
Arxiv: arxiv.org/abs/2510.09421
Code: github.com/VictorMorand...
🎉 PhD defense announcement!
@paulcouairon.bsky.social will defend his PhD titled "Structured Visual Representations with Foundation Models"!
🗓️When? Thursday, 4th November at 14:00
📍Where? Room 304 65/66, campus Pierre et Marie Curie, Sorbonne Université (4 place Jussieu, 75005 Paris).
Abstract ⬇️
@paulcouairon.bsky.social will defend his PhD titled "Structured Visual Representations with Foundation Models"!
🗓️When? Thursday, 4th November at 14:00
📍Where? Room 304 65/66, campus Pierre et Marie Curie, Sorbonne Université (4 place Jussieu, 75005 Paris).
Abstract ⬇️
October 27, 2025 at 4:44 PM
🎉 PhD defense announcement!
@paulcouairon.bsky.social will defend his PhD titled "Structured Visual Representations with Foundation Models"!
🗓️When? Thursday, 4th November at 14:00
📍Where? Room 304 65/66, campus Pierre et Marie Curie, Sorbonne Université (4 place Jussieu, 75005 Paris).
Abstract ⬇️
@paulcouairon.bsky.social will defend his PhD titled "Structured Visual Representations with Foundation Models"!
🗓️When? Thursday, 4th November at 14:00
📍Where? Room 304 65/66, campus Pierre et Marie Curie, Sorbonne Université (4 place Jussieu, 75005 Paris).
Abstract ⬇️
During today's team meeting, Marc Lafon from @lecnam.bsky.social presented his recent paper, accepted at @iccv.bsky.social 🏝️: "Learning vision-language uncertainties for failure prediction" (arxiv.org/abs/2507.07620)
October 13, 2025 at 11:53 AM
During today's team meeting, Marc Lafon from @lecnam.bsky.social presented his recent paper, accepted at @iccv.bsky.social 🏝️: "Learning vision-language uncertainties for failure prediction" (arxiv.org/abs/2507.07620)
"GaussRender: Learning 3D Occupancy with Gaussian Rendering" from Loïck Chambon, Eloi Zablocki , Alexandre BOULCH, Mickael Chen, Matthieu Cord, in collaboration with @valeoai.bsky.social.
Paper and code ⬇️
📑 arxiv.org/abs/2502.05040
🖥️ github.com/valeoai/Gaus...
Paper and code ⬇️
📑 arxiv.org/abs/2502.05040
🖥️ github.com/valeoai/Gaus...
October 2, 2025 at 4:30 PM
"GaussRender: Learning 3D Occupancy with Gaussian Rendering" from Loïck Chambon, Eloi Zablocki , Alexandre BOULCH, Mickael Chen, Matthieu Cord, in collaboration with @valeoai.bsky.social.
Paper and code ⬇️
📑 arxiv.org/abs/2502.05040
🖥️ github.com/valeoai/Gaus...
Paper and code ⬇️
📑 arxiv.org/abs/2502.05040
🖥️ github.com/valeoai/Gaus...
"DIP: Unsupervised Dense In-Context Post-training of Visual Representations" from @ssirko.bsky.social , @spyrosgidaris.bsky.social, @vobeckya.bsky.social, @abursuc.bsky.social and Nicolas Thome, with @valeoai.bsky.social.
Paper and code ⬇️
📑 arxiv.org/abs/2506.18463
🖥️ github.com/sirkosophia/...
Paper and code ⬇️
📑 arxiv.org/abs/2506.18463
🖥️ github.com/sirkosophia/...
October 2, 2025 at 4:30 PM
"DIP: Unsupervised Dense In-Context Post-training of Visual Representations" from @ssirko.bsky.social , @spyrosgidaris.bsky.social, @vobeckya.bsky.social, @abursuc.bsky.social and Nicolas Thome, with @valeoai.bsky.social.
Paper and code ⬇️
📑 arxiv.org/abs/2506.18463
🖥️ github.com/sirkosophia/...
Paper and code ⬇️
📑 arxiv.org/abs/2506.18463
🖥️ github.com/sirkosophia/...
Holidays are already over (sigh) but team's meetings are back for another year! 🔬
Today, we're listening to Jayneel Parekh, post-doc student under the supervision of @matthieucord.bsky.social , talking about his recent work: "Learning to Steer: Input-dependent Steering for Multimodal LLMs"
Today, we're listening to Jayneel Parekh, post-doc student under the supervision of @matthieucord.bsky.social , talking about his recent work: "Learning to Steer: Input-dependent Steering for Multimodal LLMs"
September 22, 2025 at 11:41 AM
Holidays are already over (sigh) but team's meetings are back for another year! 🔬
Today, we're listening to Jayneel Parekh, post-doc student under the supervision of @matthieucord.bsky.social , talking about his recent work: "Learning to Steer: Input-dependent Steering for Multimodal LLMs"
Today, we're listening to Jayneel Parekh, post-doc student under the supervision of @matthieucord.bsky.social , talking about his recent work: "Learning to Steer: Input-dependent Steering for Multimodal LLMs"
📸 Some snapshots from the #ACL2025 conference last week!
Bravo for the MLIA people! Thanks a lot to all the insightful discussions!
Recap' of the team's activities
bsky.app/profile/mlia...
#NLP #ACL
Bravo for the MLIA people! Thanks a lot to all the insightful discussions!
Recap' of the team's activities
bsky.app/profile/mlia...
#NLP #ACL
August 7, 2025 at 1:32 PM
📸 Some snapshots from the #ACL2025 conference last week!
Bravo for the MLIA people! Thanks a lot to all the insightful discussions!
Recap' of the team's activities
bsky.app/profile/mlia...
#NLP #ACL
Bravo for the MLIA people! Thanks a lot to all the insightful discussions!
Recap' of the team's activities
bsky.app/profile/mlia...
#NLP #ACL
The defense is starting!
If you cannot attend in person, follow online! ⬇️
www.youtube.com/live/CYGxEin...
If you cannot attend in person, follow online! ⬇️
www.youtube.com/live/CYGxEin...
July 10, 2025 at 12:12 PM
The defense is starting!
If you cannot attend in person, follow online! ⬇️
www.youtube.com/live/CYGxEin...
If you cannot attend in person, follow online! ⬇️
www.youtube.com/live/CYGxEin...
- "Improving Diversity in Language Models: When Temperature Fails, Change the Loss" from Alexandre Verine, Florian Le Bronnec, Kunhao Zheng, Alexandre Allauzen, Yann Chevaleyre, Benjamin Negrevergne, with Miles lab from PSL
📄 openreview.net/forum?id=Rsy...
👤 Poster: Wed 16 Jul 11 a.m. - 1:30 p.m.
📄 openreview.net/forum?id=Rsy...
👤 Poster: Wed 16 Jul 11 a.m. - 1:30 p.m.
July 9, 2025 at 9:21 AM
- "Improving Diversity in Language Models: When Temperature Fails, Change the Loss" from Alexandre Verine, Florian Le Bronnec, Kunhao Zheng, Alexandre Allauzen, Yann Chevaleyre, Benjamin Negrevergne, with Miles lab from PSL
📄 openreview.net/forum?id=Rsy...
👤 Poster: Wed 16 Jul 11 a.m. - 1:30 p.m.
📄 openreview.net/forum?id=Rsy...
👤 Poster: Wed 16 Jul 11 a.m. - 1:30 p.m.
- "Zebra: In-Context Generative Pretraining for Solving Parametric PDEs" from Louis Serrano, @armandkassai.bsky.social, Thomas Wang, Pierre ERBACHER, Patrick Gallinari
📄 arxiv.org/abs/2410.03437
🖥️ github.com/LouisSerrano...
👤 Poster: Thu 17 Jul 11 a.m. PDT — 1:30 p.m. PDT
📄 arxiv.org/abs/2410.03437
🖥️ github.com/LouisSerrano...
👤 Poster: Thu 17 Jul 11 a.m. PDT — 1:30 p.m. PDT
July 9, 2025 at 9:21 AM
- "Zebra: In-Context Generative Pretraining for Solving Parametric PDEs" from Louis Serrano, @armandkassai.bsky.social, Thomas Wang, Pierre ERBACHER, Patrick Gallinari
📄 arxiv.org/abs/2410.03437
🖥️ github.com/LouisSerrano...
👤 Poster: Thu 17 Jul 11 a.m. PDT — 1:30 p.m. PDT
📄 arxiv.org/abs/2410.03437
🖥️ github.com/LouisSerrano...
👤 Poster: Thu 17 Jul 11 a.m. PDT — 1:30 p.m. PDT
- "DISCO: learning to DISCover an evolution Operator for multi-physics-agnostic prediction" from @rdmorel.bsky.social, @jiequnh.bsky.social, Edouard Oyallon, in collaboration with #FlatironCCM.
📄 arxiv.org/abs/2504.19496
👤 Poster: Wed 16 Jul 11 a.m. PDT — 1:30 p.m. PDT
📄 arxiv.org/abs/2504.19496
👤 Poster: Wed 16 Jul 11 a.m. PDT — 1:30 p.m. PDT
July 9, 2025 at 9:21 AM
- "DISCO: learning to DISCover an evolution Operator for multi-physics-agnostic prediction" from @rdmorel.bsky.social, @jiequnh.bsky.social, Edouard Oyallon, in collaboration with #FlatironCCM.
📄 arxiv.org/abs/2504.19496
👤 Poster: Wed 16 Jul 11 a.m. PDT — 1:30 p.m. PDT
📄 arxiv.org/abs/2504.19496
👤 Poster: Wed 16 Jul 11 a.m. PDT — 1:30 p.m. PDT
CORIA-TALN recap'! ☀️
Last week, the team was in Marseille to attend to the CORIA-TALN conference. The team was presenting several posters, workshops and oral presentations!
💡 Interested in participating to the MaTOS ANR's experiment?
➡️ anr-matos.github.io/posts/2025/j...
Last week, the team was in Marseille to attend to the CORIA-TALN conference. The team was presenting several posters, workshops and oral presentations!
💡 Interested in participating to the MaTOS ANR's experiment?
➡️ anr-matos.github.io/posts/2025/j...
July 8, 2025 at 11:50 AM
CORIA-TALN recap'! ☀️
Last week, the team was in Marseille to attend to the CORIA-TALN conference. The team was presenting several posters, workshops and oral presentations!
💡 Interested in participating to the MaTOS ANR's experiment?
➡️ anr-matos.github.io/posts/2025/j...
Last week, the team was in Marseille to attend to the CORIA-TALN conference. The team was presenting several posters, workshops and oral presentations!
💡 Interested in participating to the MaTOS ANR's experiment?
➡️ anr-matos.github.io/posts/2025/j...
🎉 PhD defense announcement!
Song Duong will defend his PhD "Faithful and Efficient Conditional Text Generation for Data-to-text and Summarization"!
🗓️ Thursday, 10th July at 14:00
📍 Amphithéâtre Herpin, Bâtiment Esclangon, 4 place Jussieu, 75005 Paris.
Abstract ⬇️
Song Duong will defend his PhD "Faithful and Efficient Conditional Text Generation for Data-to-text and Summarization"!
🗓️ Thursday, 10th July at 14:00
📍 Amphithéâtre Herpin, Bâtiment Esclangon, 4 place Jussieu, 75005 Paris.
Abstract ⬇️
July 8, 2025 at 8:56 AM
🎉 PhD defense announcement!
Song Duong will defend his PhD "Faithful and Efficient Conditional Text Generation for Data-to-text and Summarization"!
🗓️ Thursday, 10th July at 14:00
📍 Amphithéâtre Herpin, Bâtiment Esclangon, 4 place Jussieu, 75005 Paris.
Abstract ⬇️
Song Duong will defend his PhD "Faithful and Efficient Conditional Text Generation for Data-to-text and Summarization"!
🗓️ Thursday, 10th July at 14:00
📍 Amphithéâtre Herpin, Bâtiment Esclangon, 4 place Jussieu, 75005 Paris.
Abstract ⬇️
🗓️ Back from a 3-months exchange at KTH university in the TMH division, @teoguiguix.bsky.social presents his work during the team meeting of the week!
July 7, 2025 at 12:07 PM
🗓️ Back from a 3-months exchange at KTH university in the TMH division, @teoguiguix.bsky.social presents his work during the team meeting of the week!
Accepted long paper at IWSLT 2025! 🥳
📆 31 July-1 August 2025
📍 Vienna, Austria
Prompting LLMs: Length Control for Isometric Machine Translation, by Dávid Javorský, Ondřej Bojar, @yvofr.bsky.social, in collaboration with @ufal-cuni.bsky.social .
📆 31 July-1 August 2025
📍 Vienna, Austria
Prompting LLMs: Length Control for Isometric Machine Translation, by Dávid Javorský, Ondřej Bojar, @yvofr.bsky.social, in collaboration with @ufal-cuni.bsky.social .
June 20, 2025 at 4:45 PM
Accepted long paper at IWSLT 2025! 🥳
📆 31 July-1 August 2025
📍 Vienna, Austria
Prompting LLMs: Length Control for Isometric Machine Translation, by Dávid Javorský, Ondřej Bojar, @yvofr.bsky.social, in collaboration with @ufal-cuni.bsky.social .
📆 31 July-1 August 2025
📍 Vienna, Austria
Prompting LLMs: Length Control for Isometric Machine Translation, by Dávid Javorský, Ondřej Bojar, @yvofr.bsky.social, in collaboration with @ufal-cuni.bsky.social .