Mark Ibrahim

Computer Science · Physical Sciences

10h-index622citations50works2.22yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Domain Adaptation and Few-Shot Learning(13), Advanced Neural Network Applications(7), Generative Adversarial Networks and Image Synthesis(6), Machine Learning and Data Classification(6), Adversarial Robustness in Machine Learning(5)

Publications49 total

OpenApps: Simulating Environment Variations to Measure UI-Agent Reliability
arXiv (Cornell University)·2025Open Access
What's in Common? Multimodal Models Hallucinate When Reasoning Across Scenes
arXiv (Cornell University)·2025Open Access
LLM Knowledge is Brittle: Truthfulness Representations Rely on Superficial Resemblance
arXiv (Cornell University)·2025Open Access
A Single Character can Make or Break Your LLM Evals
arXiv (Cornell University)·2025Open Access
AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions
arXiv (Cornell University)·2025Open Access
Joint Embedding vs Reconstruction: Provable Benefits of Latent Space Prediction for Self Supervised Learning
arXiv (Cornell University)·2025· 1 citedOpen Access
EvalGIM: A Library for Evaluating Generative Image Models
arXiv (Cornell University)·2024Open Access
Transformers Can Navigate Mazes With Multi-Step Prediction
arXiv (Cornell University)·2024· 1 citedOpen Access
UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling
arXiv (Cornell University)·2024Open Access
$\mathbb{X}$-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs
arXiv (Cornell University)·2024Open Access
Occam's Razor for Self Supervised Learning: What is Sufficient to Learn Good Representations?
arXiv (Cornell University)·2024Open Access
The Factorization Curse: Which Tokens You Predict Underlie the Reversal Curse and More
arXiv (Cornell University)·2024· 2 citedOpen Access
An Introduction to Vision-Language Modeling
arXiv (Cornell University)·2024· 33 citedOpen Access
Modeling Caption Diversity in Contrastive Vision-Language Pretraining
arXiv (Cornell University)·2024Open Access
Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinations
arXiv (Cornell University)·2024· 2 citedOpen Access
The Bias of Harmful Label Associations in Vision-Language Models
arXiv (Cornell University)·2024Open Access
UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling
2024
The Factorization Curse: Which Tokens You Predict Underlie the Reversal Curse and More
2024
Understanding the Detrimental Class-level Effects of Data Augmentation
arXiv (Cornell University)·2023· 2 citedOpen Access
WorldSense: A Synthetic Benchmark for Grounded Reasoning in Large Language Models
arXiv (Cornell University)·2023· 1 citedOpen Access
page 1 of 3Next →

Frequent Co-authors

Diane Bouchacourt(21), Randall Balestriero(9), Caner Hazırbaş(9), Ivan Evtimov(7), Ari S. Morcos(6), Polina Kirichenko(6), Quentin Garrido(5), Ceena Modarres(5), John Paisley(5), Melissa Hall(5), Florian Bordes(4), Karen Ullrich(4), Cristian Canton Ferrer(4), P. Vincent(4), Adina Williams(4), Mike Rabbat(4), Andrew Gordon Wilson(3), Melissa Louie(3), Candace Ross(3), Haider Al-Tahan(3)