4 citations · 6 across the 27 of their papers we have counts for
31 papers
Program-Verified Self-Evolution for Vision-Language Models
Ahmed Heakl, Sungik Choi, Moontae Lee +1
Self-evolving vision-language models train on questions they generate from unlabeled images. Since these questions have no gold answers, prior methods label them by majority vote o…
MedRoundsQA: A Persona and Difficulty Aware Evaluation for Multi-Turn Medical Consultations
Youssef Mohamed, Ahmed Heakl, Qinrong Cui +13
Medical benchmarks are dominated by single-turn, multiple-choice clinical cases that poorly reflect real consultations. Practically, clinicians elicit evidence interactively and pa…
Right Frame, Wrong Rule: Cultural Cues Expose the Financial Knowledge Gap They Were Meant to Close
Rania Elbadry, Ahmed Heakl, Saeed Almheiri +12
When a question has valid answers under different normative frameworks, a language model must decide which framework to use and whether it can answer correctly within it. We call t…
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…
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…
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Large language models confidently produce outdated answers, and no existing method can detect them.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,…
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…
WorldCache: Content-Aware Caching for Accelerated Video World Models
Umair Nawaz, Ahmed Heakl, Ufaq Khan +3
Diffusion Transformers (DiTs) power high-fidelity video world models but remain computationally expensive due to sequential denoising and costly spatio-temporal attention. Training…
Latent-DARM: Bridging Discrete Diffusion And Autoregressive Models For Reasoning
Lina Berrayana, Ahmed Heakl, Abdullah Sohail +3
Most multi-agent systems rely exclusively on autoregressive language models (ARMs) that are based on sequential generation. Although effective for fluent text, ARMs limit global re…
MASEval: Extending Multi-Agent Evaluation from Models to Systems
Cornelius Emde, Alexander Rubinstein, Anmol Goel +4
The rapid adoption of LLM-based agentic systems has produced a rich ecosystem of frameworks (smolagents, LangGraph, AutoGen, CAMEL, LlamaIndex, i.a.). Yet existing benchmarks are m…
Mobile-O: Unified Multimodal Understanding and Generation on Mobile Device
Abdelrahman Shaker, Ahmed Heakl, Jaseel Muhammad +8
Unified multimodal models can both understand and generate visual content within a single architecture. Existing models, however, remain data-hungry and too heavy for deployment on…
Planner and Executor: Collaboration between Discrete Diffusion And Autoregressive Models in Reasoning
Lina Berrayana, Ahmed Heakl, Muhammad Abdullah Sohail +3
Current autoregressive language models (ARMs) achieve high accuracy but require long token sequences, making them costly. Discrete diffusion language models (DDLMs) enable parallel…
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…
How Good are Foundation Models in Step-by-Step Embodied Reasoning?
Dinura Dissanayake, Ahmed Heakl, Omkar Thawakar +9
Embodied agents operating in the physical world must make decisions that are not only effective but also safe, spatially coherent, and grounded in context. While recent advances in…
VideoMolmo: Spatio-Temporal Grounding Meets Pointing
Ghazi Shazan Ahmad, Ahmed Heakl, Hanan Gani +4
Spatio-temporal localization is vital for precise interactions across diverse domains, from biological research to autonomous navigation and interactive interfaces. Current video-b…
Guaranteed Guess: A Language Modeling Approach for CISC-to-RISC Transpilation with Testing Guarantees
Ahmed Heakl, Sarim Hashmi, Chaimaa Abi +2
The hardware ecosystem is rapidly evolving, with increasing interest in translating low-level programs across different instruction set architectures (ISAs) in a quick, flexible, a…
SVRPBench: A Realistic Benchmark for Stochastic Vehicle Routing Problem
Ahmed Heakl, Yahia Salaheldin Shaaban, Martin Takac +2
Robust routing under uncertainty is central to real-world logistics, yet most benchmarks assume static, idealized settings. We present SVRPBench, the first open benchmark to captur…
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…
AIN: The Arabic INclusive Large Multimodal Model
Ahmed Heakl, Sara Ghaboura, Omkar Thawkar +4
Amid the swift progress of large language models (LLMs) and their evolution into large multimodal models (LMMs), significant strides have been made in high-resource languages such…
KITAB-Bench: A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding
Ahmed Heakl, Abdullah Sohail, Mukul Ranjan +7
With the growing adoption of Retrieval-Augmented Generation (RAG) in document processing, robust text recognition has become increasingly critical for knowledge extraction. While O…
LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs
Omkar Thawakar, Dinura Dissanayake, Ketan More +12
Reasoning is a fundamental capability for solving complex multi-step problems, particularly in visual contexts where sequential step-wise understanding is essential. Existing appro…
From CISC to RISC: language-model guided assembly transpilation
Ahmed Heakl, Chaimaa Abi, Rania Hossam +1
The transition from x86 to ARM architecture is becoming increasingly common across various domains, primarily driven by ARM's energy efficiency and improved performance across trad…
CAMEL-Bench: A Comprehensive Arabic LMM Benchmark
Sara Ghaboura, Ahmed Heakl, Omkar Thawakar +7
Recent years have witnessed a significant interest in developing large multimodal models (LMMs) capable of performing various visual reasoning and understanding tasks. This has led…
Precision Aquaculture: An Integrated Computer Vision and IoT Approach for Optimized Tilapia Feeding
Rania Hossam, Ahmed Heakl, Walid Gomaa
Traditional fish farming practices often lead to inefficient feeding, resulting in environmental issues and reduced productivity. We developed an innovative system combining comput…