IA
Ibrahim Alabdulmohsin
cs.LGcs.AIcs.CVstat.MLcs.CLmath.CAcs.ITmath.ITmath.NTcs.CY
On Valency
published · living versionsW_vu5dc8qp·v1 · currentpublished
EmbeddingGemma 2: Unified and Efficient Multimodal Representations
with Henrique Schechter Vera, Sahil Dua, Jovan Andonov, Sara Smoot +68
1 version
Preprints & journals
36 papers in the corpus · 2008–2026Gemma 4 Technical Report2607.02770v2 · Gemma Team: Sherif El Abd, Vaibhav Aggarwal, Robin Algayres et al.2026 · 8 citationsarXiv
SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features2502.14786v1 · Michael Tschannen, Alexey Gritsenko, Xiao Wang et al.2025 · 22 citationsarXiv
A Tale of Two Structures: Do LLMs Capture the Fractal Complexity of Language?2502.14924v2 · Ibrahim Alabdulmohsin, Andreas Steiner2025 · 0 citationsarXiv
Recursive Inference Scaling: A Winning Path to Scalable Inference in Language and Multimodal Systems2502.07503v4 · Ibrahim Alabdulmohsin, Xiaohua Zhai2025 · 0 citationsarXiv
Scaling Pre-training to One Hundred Billion Data for Vision Language Models2502.07617v2 · Xiao Wang, Ibrahim Alabdulmohsin, Daniel Salz et al.2025 · 3 citationsarXiv
PaliGemma 2: A Family of Versatile VLMs for Transfer2412.03555v1 · Andreas Steiner, Andr'e Susano Pinto, Michael Tschannen et al.2024 · 14 citationsarXiv
PaliGemma: A versatile 3B VLM for transfer2407.07726v2 · Lucas Beyer, Andreas Steiner, Andr'e Susano Pinto et al.2024 · 17 citationsarXiv
No Filter: Cultural and Socioeconomic Diversity in Contrastive Vision-Language Models2405.13777v3 · Ang'eline Pouget, Lucas Beyer, Emanuele Bugliarello et al.2024 · 1 citationarXiv
LocCa: Visual Pretraining with Location-aware Captioners2403.19596v2 · Bo Wan, Michael Tschannen, Yongqin Xian et al.2024 · 5 citationsarXiv
CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?2403.04547v1 · Ibrahim Alabdulmohsin, Xiao Wang, Andreas Steiner et al.2024 · 5 citationsICLR 2024
Fractal Patterns May Illuminate the Success of Next-Token Prediction2402.01825v2 · Ibrahim Alabdulmohsin, Vinh Q. Tran, Mostafa Dehghani2024 · 2 citationsarXiv
PaLI-3 Vision Language Models: Smaller, Faster, Stronger2310.09199v2 · Xi Chen, Xiao Wang, Lucas Beyer et al.2023 · 27 citationsarXiv
Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution2307.06304v1 · Mostafa Dehghani, Basil Mustafa, Josip Djolonga et al.2023 · 45 citationsarXiv
PaLI-X: On Scaling up a Multilingual Vision and Language Model2305.18565v1 · Xi Chen, Josip Djolonga, Piotr Padlewski et al.2023 · 42 citationsarXiv
Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design2305.13035v5 · Ibrahim Alabdulmohsin, Xiaohua Zhai, Alexander Kolesnikov et al.2023 · 13 citations37th Conference on Neural Information Processing Systems (NeurIPS 2023)
Scaling Vision Transformers to 22 Billion Parameters2302.05442v1 · Mostafa Dehghani, Josip Djolonga, Basil Mustafa et al.2023 · 112 citationsarXiv
Adapting to Latent Subgroup Shifts via Concepts and Proxies2212.11254v1 · Ibrahim Alabdulmohsin, Nicole Chiou, Alexander D'Amour et al.2022 · 2 citationsarXiv
FlexiViT: One Model for All Patch Sizes2212.08013v2 · Lucas Beyer, Pavel Izmailov, Alexander Kolesnikov et al.2022 · 104 citationsarXiv
Layer-Stack Temperature Scaling2211.10193v1 · Amr Khalifa, Michael C. Mozer, Hanie Sedghi et al.2022 · 0 citationsarXiv
Revisiting Neural Scaling Laws in Language and Vision2209.06640v2 · Ibrahim Alabdulmohsin, Behnam Neyshabur, Xiaohua Zhai2022 · 41 citationsNeural Information Processing Systems (NeurIPS), 2022
A Reduction to Binary Approach for Debiasing Multiclass Datasets2205.15860v2 · Ibrahim Alabdulmohsin, Jessica Schrouff, Oluwasanmi Koyejo2022 · 3 citationsIn Neural Information Processing Systems (NeurIPS), 2022
Diagnosing failures of fairness transfer across distribution shift in real-world medical settings2202.01034v2 · Jessica Schrouff, Natalie Harris, Oluwasanmi Koyejo et al.2022 · 37 citationsAdvances in Neural Information Processing Systems 35 (NeurIPS 2022)
Fair Wrapping for Black-box Predictions2201.12947v3 · Alexander Soen, Ibrahim Alabdulmohsin, Sanmi Koyejo et al.2022 · 2 citationsarXiv
The Impact of Reinitialization on Generalization in Convolutional Neural Networks2109.00267v1 · Ibrahim Alabdulmohsin, Hartmut Maennel, Daniel Keysers2021 · 4 citationsarXiv
A Generalized Lottery Ticket Hypothesis2107.06825v2 · Ibrahim Alabdulmohsin, Larisa Markeeva, Daniel Keysers et al.2021 · 4 citationsarXiv
A Generalization of Classical Formulas in Numerical Integration and Series Convergence Acceleration2106.07621v1 · Ibrahim Alabdulmohsin2021 · 0 citationsarXiv
A Near-Optimal Algorithm for Debiasing Trained Machine Learning Models2106.12887v3 · Ibrahim Alabdulmohsin, Mario Lucic2021 · 13 citationsProceedings of the Advances in Neural Information Processing Systems (NeurIPS), 2021
What Do Neural Networks Learn When Trained With Random Labels?2006.10455v2 · Hartmut Maennel, Ibrahim Alabdulmohsin, Ilya Tolstikhin et al.2020 · 47 citationsarXiv
Fair Classification via Unconstrained Optimization2005.14621v1 · Ibrahim Alabdulmohsin2020 · 2 citationsarXiv
Towards a Unified Theory of Learning and Information.33286212 · Alabdulmohsin, Ibrahim2020 · 8 citationsEntropy (Basel, Switzerland). 2020;22(4)
Fractional Parts and their Relations to the Values of the Riemann Zeta Function1701.04883v1 · Ibrahim Alabdulmohsin2017 · 1 citationarXiv
Uniform Generalization, Concentration, and Adaptive Learning1608.06072v2 · Ibrahim Alabdulmohsin2016 · 2 citationsarXiv
A new summability method for divergent series1604.07015v1 · Ibrahim M. Alabdulmohsin2016 · 0 citationsarXiv
A Mathematical Theory of Learning1405.1513v1 · Ibrahim Alabdulmohsin2014 · 0 citationsarXiv
Summability Calculus1209.5739v1 · Ibrahim M. Alabdulmohsin2012 · 0 citationsarXiv
On a New Alternative Mathematical Model for Special Relativity0803.3333v2 · Ibrahim M. Alabdulmohsin2008 · 0 citationsarXiv
Career total: 67 works. 36 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.