PlantIF: multimodal graph learning for plant disease diagnosis. Fuses image-text features via semantic encoders and self-attention GCN. 96.95% accuracy on 205K images. #PlantDisease #MultimodalLearning #PrecisionAgriculture
Details: doi.org/10.1016/j.pl...
Details: doi.org/10.1016/j.pl...
September 25, 2026 at 12:51 PM
PlantIF: multimodal graph learning for plant disease diagnosis. Fuses image-text features via semantic encoders and self-attention GCN. 96.95% accuracy on 205K images. #PlantDisease #MultimodalLearning #PrecisionAgriculture
Details: doi.org/10.1016/j.pl...
Details: doi.org/10.1016/j.pl...
Over several years, we’ve contributed #research to @iclr-conf.bsky.social exploring how #machinelearning models are trained, interpreted, and applied. This year’s papers span #multimodallearning, #diffusion, interpretability, and theory, with open #code and demos.
🔗 bit.ly/4eFumVs
🔗 bit.ly/4eFumVs
April 24, 2026 at 12:06 AM
Over several years, we’ve contributed #research to @iclr-conf.bsky.social exploring how #machinelearning models are trained, interpreted, and applied. This year’s papers span #multimodallearning, #diffusion, interpretability, and theory, with open #code and demos.
🔗 bit.ly/4eFumVs
🔗 bit.ly/4eFumVs
Research says: Physical activities that engage multiple senses, like drawing or acting out words, can boost understanding and retention! 🖍️🕺
Find out how: edut.to/43V2G9Z
#EdResearch #EduSky #MultimodalLearning
Find out how: edut.to/43V2G9Z
#EdResearch #EduSky #MultimodalLearning
The Power of Multimodal Learning (in 5 Charts)
When students engage multiple senses to learn—drawing or acting out a concept, for example—they’re more likely to remember and develop a deeper understanding of the material, a large body of research…
edut.to
June 20, 2025 at 1:06 PM
Research says: Physical activities that engage multiple senses, like drawing or acting out words, can boost understanding and retention! 🖍️🕺
Find out how: edut.to/43V2G9Z
#EdResearch #EduSky #MultimodalLearning
Find out how: edut.to/43V2G9Z
#EdResearch #EduSky #MultimodalLearning
Emory University and Georgia Tech are recruiting a Postdoctoral Fellow in Machine Learning and Multimodal AI to develop novel methods...
mlscientist.com/postdoc-mult...
#machinelearning #multimodallearning #computervision
mlscientist.com/postdoc-mult...
#machinelearning #multimodallearning #computervision
September 20, 2026 at 2:48 PM
Emory University and Georgia Tech are recruiting a Postdoctoral Fellow in Machine Learning and Multimodal AI to develop novel methods...
mlscientist.com/postdoc-mult...
#machinelearning #multimodallearning #computervision
mlscientist.com/postdoc-mult...
#machinelearning #multimodallearning #computervision
#ICML2026 #MachineLearning #MultimodalLearning #RepresentationLearning #OptimalTransport #VisionLanguage #Alignment
July 3, 2026 at 9:18 AM
Want students to remember what they’ve learned? Get them moving and engaging multiple senses! Here are 5 research-backed strategies to boost their understanding *and* retention. 🕺🤸
#EdResearch #EduSky #MultimodalLearning
#EdResearch #EduSky #MultimodalLearning
The Power of Multimodal Learning (in 5 Charts)
When students engage multiple senses to learn—drawing or acting out a concept, for example—they’re more likely to remember and develop a deeper understanding of the material, a large body of research…
www.edutopia.org
October 1, 2025 at 10:28 AM
Want students to remember what they’ve learned? Get them moving and engaging multiple senses! Here are 5 research-backed strategies to boost their understanding *and* retention. 🕺🤸
#EdResearch #EduSky #MultimodalLearning
#EdResearch #EduSky #MultimodalLearning
Happy to share our paper on MultimodalLearning of Low-Dimensional Latent Dynamics, published in J of Neural Eng! lnkd.in/gThxnUZg
👇 Summary 🧵
Many thanks to my brilliant co-authors, Omid Sani and Bijan Pesaran, and my amazing PhD advisor, @maryamshanechi.bsky.social.
👇 Summary 🧵
Many thanks to my brilliant co-authors, Omid Sani and Bijan Pesaran, and my amazing PhD advisor, @maryamshanechi.bsky.social.
Can we efficiently learn models of collective dynamics in multimodal discrete-continuous time-series, e.g., spike-LFP?
We develop a multimodal subspace identification method to do so & enable causal multimodal decoding!
👏P Ahmadipour!
📜J Neural Eng Paper: iopscience.iop.org/article/10.1...
Code+🧵⬇️
We develop a multimodal subspace identification method to do so & enable causal multimodal decoding!
👏P Ahmadipour!
📜J Neural Eng Paper: iopscience.iop.org/article/10.1...
Code+🧵⬇️
December 19, 2024 at 12:51 AM
Happy to share our paper on MultimodalLearning of Low-Dimensional Latent Dynamics, published in J of Neural Eng! lnkd.in/gThxnUZg
👇 Summary 🧵
Many thanks to my brilliant co-authors, Omid Sani and Bijan Pesaran, and my amazing PhD advisor, @maryamshanechi.bsky.social.
👇 Summary 🧵
Many thanks to my brilliant co-authors, Omid Sani and Bijan Pesaran, and my amazing PhD advisor, @maryamshanechi.bsky.social.
Time-Series Forecasting and Refinement Within a Multimodal PDE Foundation Model
www.dl.begellhouse.com/journals/558...
#MultimodalLearning #TimeSeriesForecasting #ArtificialIntelligence
www.dl.begellhouse.com/journals/558...
#MultimodalLearning #TimeSeriesForecasting #ArtificialIntelligence
September 10, 2025 at 5:43 PM
Time-Series Forecasting and Refinement Within a Multimodal PDE Foundation Model
www.dl.begellhouse.com/journals/558...
#MultimodalLearning #TimeSeriesForecasting #ArtificialIntelligence
www.dl.begellhouse.com/journals/558...
#MultimodalLearning #TimeSeriesForecasting #ArtificialIntelligence
💡 Revisiting my article on Visual Thinking Strategies in Danish classrooms (Journal of Visual Literacy).
It explores how VTS supports bildung and democratic pedagogy—still timely for inclusive, multimodal teaching.
🔗 doi.org/10.1080/1051...
#MultimodalLearning #EdResearch
It explores how VTS supports bildung and democratic pedagogy—still timely for inclusive, multimodal teaching.
🔗 doi.org/10.1080/1051...
#MultimodalLearning #EdResearch
Visual thinking strategies as a pedagogical tool: initial expectations, applications, and perspectives in Denmark
This paper examines the introduction of Visual Thinking Strategies (VTS) in Denmark and its potential as a pedagogical tool used throughout Danish education culture and particularly in Danish prima...
doi.org
November 2, 2025 at 2:27 PM
💡 Revisiting my article on Visual Thinking Strategies in Danish classrooms (Journal of Visual Literacy).
It explores how VTS supports bildung and democratic pedagogy—still timely for inclusive, multimodal teaching.
🔗 doi.org/10.1080/1051...
#MultimodalLearning #EdResearch
It explores how VTS supports bildung and democratic pedagogy—still timely for inclusive, multimodal teaching.
🔗 doi.org/10.1080/1051...
#MultimodalLearning #EdResearch
"Unlock the future of human-computer interaction with multimodal learning! 🤖 Discover the latest trends in AI, Machine Learning & more #MultimodalLearning #AI #MachineLearning"
🔗 https://bytejournal.online/blog/multimodal-learning-demystified
🔗 https://bytejournal.online/blog/multimodal-learning-demystified
"Unlock the future of human-computer interaction with multimodal learning! 🤖 Discover the latest tre
bytejournal.online
March 11, 2026 at 5:49 AM
"Unlock the future of human-computer interaction with multimodal learning! 🤖 Discover the latest trends in AI, Machine Learning & more #MultimodalLearning #AI #MachineLearning"
🔗 https://bytejournal.online/blog/multimodal-learning-demystified
🔗 https://bytejournal.online/blog/multimodal-learning-demystified
🎥 Excited to share a practical and inspiring conversation on building authentic student competencies through multimodal learning! @laproffisa
👉 Watch here: www.youtube.com/watch?v=rEV3...
#Education #Teaching #MultimodalLearning #StudentSuccess #EdInnovation
👉 Watch here: www.youtube.com/watch?v=rEV3...
#Education #Teaching #MultimodalLearning #StudentSuccess #EdInnovation
Bloom's Builder Toolkit: costruiamo competenze tenendo conto della multimodalità.
https://app.schoolai.com/dot/spaces/f737a409-26c3-4a37-b4d0-37e6bda79882
www.youtube.com
January 30, 2026 at 9:01 PM
🎥 Excited to share a practical and inspiring conversation on building authentic student competencies through multimodal learning! @laproffisa
👉 Watch here: www.youtube.com/watch?v=rEV3...
#Education #Teaching #MultimodalLearning #StudentSuccess #EdInnovation
👉 Watch here: www.youtube.com/watch?v=rEV3...
#Education #Teaching #MultimodalLearning #StudentSuccess #EdInnovation
We are wrapping up our 5th-year anniversary paper series with ViTa by Yundi Zhang et al. (www.sciencedirect.com/science/arti...), a work that adresses: How to realize personalized cardiac healthcare that moves beyond a single task?
#AIMResearch #AIMAnniversary #MultiModalLearning #CardiacMRI
#AIMResearch #AIMAnniversary #MultiModalLearning #CardiacMRI
Towards cardiac MRI foundation models: Comprehensive visual-tabular representations for whole-heart assessment and beyond
Cardiac magnetic resonance (CMR) imaging is the gold standard for non-invasive cardiac assessment, offering rich spatio-temporal views of the heart’s …
www.sciencedirect.com
October 29, 2025 at 12:19 PM
We are wrapping up our 5th-year anniversary paper series with ViTa by Yundi Zhang et al. (www.sciencedirect.com/science/arti...), a work that adresses: How to realize personalized cardiac healthcare that moves beyond a single task?
#AIMResearch #AIMAnniversary #MultiModalLearning #CardiacMRI
#AIMResearch #AIMAnniversary #MultiModalLearning #CardiacMRI
💬 Curious how others are using Visual Thinking Strategies in the classroom.
In my article, I explored how VTS connects with bildung and democratic pedagogy in Denmark.
How are you applying VTS or multimodal approaches in your teaching?
🔗 doi.org/10.1080/1051...
#MultimodalLearning #EdResearch
In my article, I explored how VTS connects with bildung and democratic pedagogy in Denmark.
How are you applying VTS or multimodal approaches in your teaching?
🔗 doi.org/10.1080/1051...
#MultimodalLearning #EdResearch
Visual thinking strategies as a pedagogical tool: initial expectations, applications, and perspectives in Denmark
This paper examines the introduction of Visual Thinking Strategies (VTS) in Denmark and its potential as a pedagogical tool used throughout Danish education culture and particularly in Danish prima...
doi.org
November 2, 2025 at 2:29 PM
💬 Curious how others are using Visual Thinking Strategies in the classroom.
In my article, I explored how VTS connects with bildung and democratic pedagogy in Denmark.
How are you applying VTS or multimodal approaches in your teaching?
🔗 doi.org/10.1080/1051...
#MultimodalLearning #EdResearch
In my article, I explored how VTS connects with bildung and democratic pedagogy in Denmark.
How are you applying VTS or multimodal approaches in your teaching?
🔗 doi.org/10.1080/1051...
#MultimodalLearning #EdResearch
Want to make learning stick? 🧠✨
Build background knowledge the right way—with videos, textures, smells, music & more.
Discover how multimodal learning makes comprehension easier and lessons more memorable.
🔗 bit.ly/4eRe0Wh
#EdTech #TeachingTips #MultimodalLearning #EducationResearch #EdEquity
Build background knowledge the right way—with videos, textures, smells, music & more.
Discover how multimodal learning makes comprehension easier and lessons more memorable.
🔗 bit.ly/4eRe0Wh
#EdTech #TeachingTips #MultimodalLearning #EducationResearch #EdEquity
May 7, 2025 at 2:25 PM
Want to make learning stick? 🧠✨
Build background knowledge the right way—with videos, textures, smells, music & more.
Discover how multimodal learning makes comprehension easier and lessons more memorable.
🔗 bit.ly/4eRe0Wh
#EdTech #TeachingTips #MultimodalLearning #EducationResearch #EdEquity
Build background knowledge the right way—with videos, textures, smells, music & more.
Discover how multimodal learning makes comprehension easier and lessons more memorable.
🔗 bit.ly/4eRe0Wh
#EdTech #TeachingTips #MultimodalLearning #EducationResearch #EdEquity
🤖 Moving Beyond Coexistence: The Path to Synergistic Unified Multimodal Models
https://pneumetron.com/news/ai_research/synergistic-unified-multimodal-models-ccc6cc
#multimodallearning #computervision #architecturedesign #generativeai
https://pneumetron.com/news/ai_research/synergistic-unified-multimodal-models-ccc6cc
#multimodallearning #computervision #architecturedesign #generativeai
September 5, 2026 at 6:43 AM
🤖 Moving Beyond Coexistence: The Path to Synergistic Unified Multimodal Models
https://pneumetron.com/news/ai_research/synergistic-unified-multimodal-models-ccc6cc
#multimodallearning #computervision #architecturedesign #generativeai
https://pneumetron.com/news/ai_research/synergistic-unified-multimodal-models-ccc6cc
#multimodallearning #computervision #architecturedesign #generativeai
🤖 SmartMage: Dynamic Modality Orchestration for 3D Scene Understanding
https://pneumetron.com/news/ai_research/smartmage-dynamic-modality-orchestration-3d-scene-understanding-f315c9
#artificialintelligence #3dvision #multimodallearning #embodiedai
https://pneumetron.com/news/ai_research/smartmage-dynamic-modality-orchestration-3d-scene-understanding-f315c9
#artificialintelligence #3dvision #multimodallearning #embodiedai
August 11, 2026 at 11:31 AM
🤖 SmartMage: Dynamic Modality Orchestration for 3D Scene Understanding
https://pneumetron.com/news/ai_research/smartmage-dynamic-modality-orchestration-3d-scene-understanding-f315c9
#artificialintelligence #3dvision #multimodallearning #embodiedai
https://pneumetron.com/news/ai_research/smartmage-dynamic-modality-orchestration-3d-scene-understanding-f315c9
#artificialintelligence #3dvision #multimodallearning #embodiedai
RefCaptioner: Bridging the Gap in Multi-Reference Video Grounding
https://pneumetron.com/news/ai_research/refcaptioner-multi-reference-video-grounding-d7fc52
#artificialintelligence #computervision #videocaptioning #multimodallearning
https://pneumetron.com/news/ai_research/refcaptioner-multi-reference-video-grounding-d7fc52
#artificialintelligence #computervision #videocaptioning #multimodallearning
July 31, 2026 at 4:59 PM
RefCaptioner: Bridging the Gap in Multi-Reference Video Grounding
https://pneumetron.com/news/ai_research/refcaptioner-multi-reference-video-grounding-d7fc52
#artificialintelligence #computervision #videocaptioning #multimodallearning
https://pneumetron.com/news/ai_research/refcaptioner-multi-reference-video-grounding-d7fc52
#artificialintelligence #computervision #videocaptioning #multimodallearning
Shallow quantum circuits efficiently augment multimodal representations, achieving superior image-text classification with 2.2K quantum parameters compared to 24K classical alternatives, and improved robustness on incomplete inputs.
#QuantumML #MultimodalLearning #Research
#QuantumML #MultimodalLearning #Research
Quantum Feature Augmentation for Multimodal Classification
arxiv.org
July 16, 2026 at 3:59 AM
Shallow quantum circuits efficiently augment multimodal representations, achieving superior image-text classification with 2.2K quantum parameters compared to 24K classical alternatives, and improved robustness on incomplete inputs.
#QuantumML #MultimodalLearning #Research
#QuantumML #MultimodalLearning #Research
We invite submissions to the MAAI Workshop: Multimodal Affect in AI for Education at the Festival of Learning (EDM, AIED, L@S) in Seoul, South Korea.
Submission deadline: April 26, 2026 (AoE)
Learn more here:🌐 multimodal-affect-ai4ed.github.io
#AIED #MultimodalLearning #AffectiveComputing
Submission deadline: April 26, 2026 (AoE)
Learn more here:🌐 multimodal-affect-ai4ed.github.io
#AIED #MultimodalLearning #AffectiveComputing
April 15, 2026 at 1:02 AM
We invite submissions to the MAAI Workshop: Multimodal Affect in AI for Education at the Festival of Learning (EDM, AIED, L@S) in Seoul, South Korea.
Submission deadline: April 26, 2026 (AoE)
Learn more here:🌐 multimodal-affect-ai4ed.github.io
#AIED #MultimodalLearning #AffectiveComputing
Submission deadline: April 26, 2026 (AoE)
Learn more here:🌐 multimodal-affect-ai4ed.github.io
#AIED #MultimodalLearning #AffectiveComputing
👉 Let’s talk multimodal learning — come by or check out the paper!
Joint work with an amazing team: @benoit-dufumier.bsky.social, D. Tuia & J-P. Thiran
#ICLR2025 #MultimodalLearning #SelfSupervisedLearning #ContrastiveLearning
Joint work with an amazing team: @benoit-dufumier.bsky.social, D. Tuia & J-P. Thiran
#ICLR2025 #MultimodalLearning #SelfSupervisedLearning #ContrastiveLearning
April 24, 2025 at 4:02 PM
👉 Let’s talk multimodal learning — come by or check out the paper!
Joint work with an amazing team: @benoit-dufumier.bsky.social, D. Tuia & J-P. Thiran
#ICLR2025 #MultimodalLearning #SelfSupervisedLearning #ContrastiveLearning
Joint work with an amazing team: @benoit-dufumier.bsky.social, D. Tuia & J-P. Thiran
#ICLR2025 #MultimodalLearning #SelfSupervisedLearning #ContrastiveLearning
A new study proposes JCSBA, joint client scheduling and bandwidth allocation for multimodal federated learning, boosting accuracy by 4% and unimodal tasks by 2‑3%. Read more: https://getnews.me/optimizing-multimodal-federated-learning-amid-modal-heterogeneity/ #multimodallearning #federatedlearning
September 18, 2025 at 1:07 PM
A new study proposes JCSBA, joint client scheduling and bandwidth allocation for multimodal federated learning, boosting accuracy by 4% and unimodal tasks by 2‑3%. Read more: https://getnews.me/optimizing-multimodal-federated-learning-amid-modal-heterogeneity/ #multimodallearning #federatedlearning
Even the hottest multimodal models stumble—capped at 50% on simple visual entity tasks. What does this reveal about current vision‑language gaps? Dive into the benchmarks and see why AI still has a long way to go. #MultimodalLearning #VisionLanguage #AIPerformance
🔗 aidailypost.com/news/top-mul...
🔗 aidailypost.com/news/top-mul...
February 8, 2026 at 1:45 PM
Even the hottest multimodal models stumble—capped at 50% on simple visual entity tasks. What does this reveal about current vision‑language gaps? Dive into the benchmarks and see why AI still has a long way to go. #MultimodalLearning #VisionLanguage #AIPerformance
🔗 aidailypost.com/news/top-mul...
🔗 aidailypost.com/news/top-mul...
I will be at EMNLP next week presenting this work on November the 7th! Reach out to me for any questions :))
Work done with my advisor, Mirella Lapata!
Preprint: arxiv.org/pdf/2505.14627
#EMNLP2025 #multimodallearning #scalableoversight #visionlanguagemodels #nlproc
Work done with my advisor, Mirella Lapata!
Preprint: arxiv.org/pdf/2505.14627
#EMNLP2025 #multimodallearning #scalableoversight #visionlanguagemodels #nlproc
arxiv.org
November 1, 2025 at 7:30 PM
I will be at EMNLP next week presenting this work on November the 7th! Reach out to me for any questions :))
Work done with my advisor, Mirella Lapata!
Preprint: arxiv.org/pdf/2505.14627
#EMNLP2025 #multimodallearning #scalableoversight #visionlanguagemodels #nlproc
Work done with my advisor, Mirella Lapata!
Preprint: arxiv.org/pdf/2505.14627
#EMNLP2025 #multimodallearning #scalableoversight #visionlanguagemodels #nlproc
Apple MM1 – Faszinierende Forschung für KI-Fortschritt
#KuenstlicheIntelligenz #artificialintelligence #KI #AI #MultimodalLearning #MachineLearning #Technology #Innovation #DataScience #AppleMM1
kinews24.de/apple-mm1/
#KuenstlicheIntelligenz #artificialintelligence #KI #AI #MultimodalLearning #MachineLearning #Technology #Innovation #DataScience #AppleMM1
kinews24.de/apple-mm1/
March 18, 2024 at 10:23 AM
Apple MM1 – Faszinierende Forschung für KI-Fortschritt
#KuenstlicheIntelligenz #artificialintelligence #KI #AI #MultimodalLearning #MachineLearning #Technology #Innovation #DataScience #AppleMM1
kinews24.de/apple-mm1/
#KuenstlicheIntelligenz #artificialintelligence #KI #AI #MultimodalLearning #MachineLearning #Technology #Innovation #DataScience #AppleMM1
kinews24.de/apple-mm1/