Author

Mohamed Eltahir

Observed name: Eltahir, Mohamed

Institution: King Abdullah University of Science and Technology

Observed institution: King Abdullah University of Science and Technology

OpenAlex ID: A5120024318

AutoArabic: A Three-Stage Framework for Localizing Video-Text Retrieval Benchmarks

2025 · Mohamed Eltahir, Osamah Sarraj, et al. · Arabic Natural Language Processing Workshop (WANLP) · 1

PDF

Periscope: Extending Frozen Language Models Beyond Their Context Window

2026 · Eltahir, Mohamed, Obayd, Anas, et al. · arXiv (Cornell University)

PDF

The Model Knows When to Stop: Training-Free Early Stopping for Long-Context Reading

2026 · Alyobi, Muath, Eltahir, Mohamed, et al. · arXiv (Cornell University)

PDF

AnswerMap: Faithful Spatial Interpretability of VLMs from Answer Posteriors

2026 · Eltahir, Mohamed, Adam, Fardows, et al. · arXiv (Cornell University)

PDF

Your Benchmark Is Not Saturated: Reviving Multiple-Choice Evaluation with Answer Pooling

2026 · Eltahir, Mohamed, Ahmed, Abobaker, et al. · arXiv (Cornell University)

PDF

Generative Late-Interaction Embeddings For Visual Document Retrieval

2026 · Eltahir, Mohamed, Aloushan, Talal, et al. · arXiv (Cornell University)

PDF

HAJJv2-CrowdCount: Zero-Shot Benchmark for Dense Crowd Counting

2026 · AlYabis, Reem, AlTuwaim, Fares, et al. · arXiv (Cornell University)

PDF

When Does Small Data Work? Accuracy and Efficiency Trade-offs Between Tabular Foundation Models and Conventional Methods for Crowd-State Classification at Hajj and Umrah

2026 · AlOtaibi, AlJawharh S., Eltahir, Mohamed, et al. · arXiv (Cornell University)

PDF

Vote-in-Context: VLMs as Explainable Zero-Shot Rank Fusers

2026 · Mohamed Eltahir, Ali Habibullah, et al.

GridProbe: Posterior-Probing for Adaptive Test-Time Compute in Long-Video VLMs

2026 · Eltahir, Mohamed, Ayash, Lama, et al. · arXiv (Cornell University)

PDF

GridVAD: Open-Set Video Anomaly Detection via Spatial Reasoning over Stratified Frame Grids

2026 · Eltahir, Mohamed, Ibrahim, Ahmed O., et al. · arXiv (Cornell University)

PDF

VideoAtlas: Navigating Long-Form Video in Logarithmic Compute

2026 · Eltahir, Mohamed, Habibullah, Ali, et al. · arXiv (Cornell University)

PDF

Vote-in-Context: Turning VLMs into Zero-Shot Rank Fusers

2025 · Eltahir, Mohamed, Habibullah, Ali, et al. · arXiv (Cornell University)

PDF

Multimodal Lengthy Videos Retrieval Framework and Evaluation Metric

2025 · Eltahir, Mohamed, Sarraj, Osamah, et al. · arXiv (Cornell University)

PDF

Works count: 14

Citation count: 1

H-index: 1

I10-index: