activity
20242026
collaborators

19 papers

cs.CL2026

DocAtlas: Multilingual Document Understanding Across 80+ Languages

Ahmed Heakl, Youssef Mohamed, Abdullah Sohail +6

Multilingual document understanding remains limited for low-resource languages due to scarce training data and model-based annotation pipelines that perpetuate existing biases. We…

cs.LG2026

CEPO: RLVR Self-Distillation using Contrastive Evidence Policy Optimization

Ahmed Heakl, Abdelrahman M. Shaker, Youssef Mohamed +4

When a model produces a correct solution under reinforcement learning with verifiable rewards (RLVR), every token receives the same reward signal regardless of whether it was a dec…

cs.CL2026

Dr.LLM: Dynamic Layer Routing in LLMs

Ahmed Heakl, Martin Gubri, Salman Khan +2

Large Language Models (LLMs) process every token through all layers of a transformer stack, causing wasted computation on simple queries and insufficient flexibility for harder one…

cs.AI2026

The Geometry of Forgetting: Temporal Knowledge Drift as an Independent Axis in LLM Representations

Rania Elbadry, Ahmed Heakl, Fan Zhang +4

Large language models confidently produce outdated answers, and no existing method can detect them. We show this is not an engineering failure but a structural one: temporal drift,…

cs.CL2026

SAHM: A Benchmark for Arabic Financial and Shari'ah-Compliant Reasoning

Rania Elbadry, Sarfraz Ahmad, Ahmed Heakl +12

English financial NLP has advanced rapidly through benchmarks targeting earnings analysis, market sentiment, tabular reasoning, and financial question answering, yet Arabic financi…

cs.AR2026

CASS: Nvidia to AMD Transpilation with Data, Models, and Benchmark

Ahmed Heakl, Gustavo Bertolo Stahl, Sarim Hashmi +5

Cross-architecture GPU code transpilation is essential for unlocking low-level hardware portability, yet no scalable solution exists. We introduce CASS, the first dataset and model…