Detecting generalization deficits in large language and reasoning models by using natural variati...
Marianna Nezhurina, Lucia Cipolina-Kun, Mehdi Cherti, Jenia Jitsev
Action editor: Elahe Arani
https://openreview.net/forum?id=frA7uYn2um
#generalization #parsing #ai
Decoding Generalization from Memorization in Deep Neural Networks
Simran Ketha, Venkatakrishnan Ramaswamy
Action editor: Takashi Ishida
https://openreview.net/forum?id=BeT6jaD6ao
#memorization #generalization #generalize
New #Expert Certification:
FedLOE: Federated Domain Generalization via Locally Overfit Ensemble
Ruqi Bai, David I. Inouye
https://openreview.net/forum?id=W4T9sK6Gai
#ensemble #federated #generalization
How Well Can Preference Optimization Generalize Under Noisy Feedback?
Shawn Im, Yixuan Li
Action editor: Huazheng Wang
https://openreview.net/forum?id=8f5gRWwzDx
#preference #preferences #generalization
Cost-Free Personalization via Information-Geometric Projection in Bayesian Federated Learning
Nour Jamoussi, Giuseppe Serra, Photios A. Stavrou, Marios Kountouris
Action editor: Feng Zhou
https://openreview.net/forum?id=9y0jCrxjDR
#personalized #personalization #generalization
Generalization Bound for a Shallow Transformer Trained Using Gradient Descent
Brian Mwigo, Anirban Dasgupta
Action editor: Yingbin Liang
https://openreview.net/forum?id=t3iUeMOT8Z
#transformer #transformers #generalization
The Initialization Determines Whether In-Context Learning Is Gradient Descent
Shifeng Xie, Rui Yuan, Simone Rossi, Thomas Hannagan
Action editor: Marwa El Halabi
https://openreview.net/forum?id=fvqSKLDtJi
#attention #embedding #generalization
Differentiated Aggregation to Improve Generalization in Federated Learning
Peyman Gholami, Hulya Seferoglu
Action editor: Sai Aparna Aketi
https://openreview.net/forum?id=F5hgpQ1Ccd
#federated #generalization #aggregations
Are Domain Generalization Benchmarks with Accuracy on the Line Misspecified?
Olawale Elijah Salaudeen, Nicole Chiou, Shiny Weng, Sanmi Koyejo
Action editor: Ozan Sener
https://openreview.net/forum?id=fNywRyqPQo
#robustness #generalization #benchmarks
Class-wise Generalization Error: an Information-Theoretic analysis
Firas Laakom, Moncef Gabbouj, Jürgen Schmidhuber, Yuheng Bu
Action editor: Gintare Dziugaite
https://openreview.net/forum?id=asW4VcDFpi
#generalization #generalizes #classes
Enabling Automatic Differentiation with Mollified Graph Neural Operators
Ryan Y. Lin, Julius Berner, Valentin Duruisseaux et al.
Action editor: Mingsheng Long
https://openreview.net/forum?id=CGoR1hFAGr
#gradients #generalization #differential
Rethinking Robustness in Machine Learning: A Posterior Agreement Approach
João B. S. Carvalho, Víctor Jiménez Rodríguez, Alessandro Torcinovich et al.
Action editor: Mohammad Emtiyaz Khan
https://openreview.net/forum?id=Bpc9uZ6kcg
#robustness #adversarial #generalization
Algorithmic Personalization of Information Can Cause Inaccurate Generalization and Overconfidence #algorithms #personalization #recommendation #information #specificity #diversity #beliefs #generalization #overconfidence #bias #learning
▫️ The age of #scaling is ending.
▫️ #Generalization is the real frontier.
▫️ #AGI will start as a #superintelligent learner, not an all-knowing oracle.
▫️ Timelines are short.
#IlyaSutskever #ArtificialGeneralIntellignce #AI #Playbook #AIPlaybook #EndOfScaling
www.the-ai-corner.com/p/ilya-sutsk...
Emergent Neural Network Mechanisms for Generalization to Objects in Novel Orientations
Avi Cooper, Daniel Harari, Tomotake Sasaki et al.
Action editor: Andrew Lampinen
https://openreview.net/forum?id=4wBQTZVSHU
#orientations #orientation #generalization
Researchers isolate memorization from reasoning in AI neural networks https://arstechni.ca #mechanisticinterpretability #computationalneuroscience #AllenInstituteforAI #transformermodels #gradientdescent #machinelearning #AIarchitecture #AImemorization #generalization #neuralnetworks…
New #J2C Certification:
Are Domain Generalization Benchmarks with Accuracy on the Line Misspecified?
Olawale Elijah Salaudeen, Nicole Chiou, Shiny Weng, Sanmi Koyejo
https://openreview.net/forum?id=fNywRyqPQo
#robustness #generalization #benchmarks
New #J2C Certification:
Class-wise Generalization Error: an Information-Theoretic analysis
Firas Laakom, Moncef Gabbouj, Jürgen Schmidhuber, Yuheng Bu
https://openreview.net/forum?id=asW4VcDFpi
#generalization #generalizes #classes
Towards Efficient Contrastive PAC Learning
Jie Shen
Action editor: Tianbao Yang
https://openreview.net/forum?id=dBJo9hyKVg
#contrastive #rademacher #generalization
New #Expert Certification:
Enabling Automatic Differentiation with Mollified Graph Neural Operators
Ryan Y. Lin, Julius Berner, Valentin Duruisseaux et al.
https://openreview.net/forum?id=CGoR1hFAGr
#gradients #generalization #differential
Understanding Generalization in Physics‑Informed Machine Learning Models
Researchers find that affine‑variety dimension—not model size—drives generalization in physics‑informed ML; linear and nonlinear PDE tests confirm the results. Read more: getnews.me/understanding-generaliza... #physicsinformedml #generalization
Top left: MRI setup (top) and task structure (bottom). Bottom left: Brain areas showing a significant main-effect of Task epoch, based on region-wise two-way repeated measures ANOVAs using a false discovery rate (FDR) correction for multiple comparisons (q < 0.05). Bottom right: Meta-analyses of the main effects depicted in A based on the NiMARE correlation decoder tool with the Neurosynth database
How does the #brain transfer #MotorSkills between hands? This study reveals that transfer relies on re-expressing the neural patterns established during initial learning in distributed higher-order brain areas, offering new insights into learning #generalization @plosbiology.org 🧪 plos.io/41LOAWf
Top left: MRI setup (top) and task structure (bottom). Bottom left: Brain areas showing a significant main-effect of Task epoch, based on region-wise two-way repeated measures ANOVAs using a false discovery rate (FDR) correction for multiple comparisons (q < 0.05). Bottom right: Meta-analyses of the main effects depicted in A based on the NiMARE correlation decoder tool with the Neurosynth database
How does the #brain transfer #MotorSkills between hands? This study reveals that transfer relies on re-expressing the neural patterns established during initial learning in distributed higher-order brain areas, offering new insights into learning #generalization @plosbiology.org 🧪 plos.io/41LOAWf
Top left: MRI setup (top) and task structure (bottom). Bottom left: Brain areas showing a significant main-effect of Task epoch, based on region-wise two-way repeated measures ANOVAs using a false discovery rate (FDR) correction for multiple comparisons (q < 0.05). Bottom right: Meta-analyses of the main effects depicted in A based on the NiMARE correlation decoder tool with the Neurosynth database
How does the #brain transfer #MotorSkills between hands? This study reveals that transfer relies on re-expressing the neural patterns established during initial learning in distributed higher-order brain areas, offering new insights into learning #generalization @plosbiology.org 🧪 plos.io/41LOAWf
Call me #Racist,
(I don’t mind; I know the truth)
#Woke,
(I try to be AWARE of my surroundings)
#Nosey,
(I like to know stuff)
but don’t call me #Lazy!
A #Statistic is a well thought out #Stereotype.
A historic #Generalization has proven to be an #AcceptedInsult.
www.salon.com/2025/08/09/t...
👇🏾
Best Theme Papers at ACL 2025! 🎉 This year's special theme is "Generalization of NLP Models," and these papers truly exemplify outstanding contributions to this critical area. #ACL2025NLP #ThemePaper #Generalization #NLProc
🌟 Had a great time presenting our poster at #ACL2025!
It was a great experience sharing our work with researchers interested in conceptual categories, #abstraction and #generalization, thanks for the insightful discussions and feedback!
wt @andreapdr.bsky.social @mariannabolog.bsky.social
#NLProc
