HH
Hakim Hacid
cs.LGcs.AIcs.CLcs.CVcs.DCcs.IRcs.MMcs.SDeess.SPcs.CR
On Valency
published · living versionsW_pa9a3ubt·v1 · currentpublished
Neither Over- nor Under-Constrained: Evaluating LLM Personalization under a Constraint Qualification Audit
with Xuran Li, Guanqin Zhang, Imran Razzak, Eleanna Kafeza +2
1 version
Preprints & journals
46 papers in the corpus · 2013–2026Neither Over- nor Under-Constrained: Evaluating LLM Personalization under a Constraint Qualification Audit2610.25676v1 · Xuran Li, Guanqin Zhang, Imran Razzak et al.2026 · 0 citationsarXivon Valency
Train Smarter, Not Longer: Memorization-Guided Data Reuse for Efficient LLM Training2607.04969v1 · Jingwei Zuo, Cong Zeng, Ilyas Chahed et al.2026 · 0 citationsarXiv
Evaluating LLM Personalization via Semantic Constraint Verification2606.16368v1 · Xuran Li, Guanqin Zhang, Imran Razzak et al.2026 · 0 citationsarXiv
Knowledge Graph Enhanced Memory-Augmented Retrieval for Long Context Modeling2606.14047v1 · Ghadir Alselwi, Basem Suleiman, Hao Xue et al.2026 · 0 citationsarXiv
Are Arabic Benchmarks Reliable? QIMMA's Quality-First Approach to LLM Evaluation2604.03395v1 · Leen AlQadi, Ahmed Alzubaidi, Mohammed Alyafeai et al.2026 · 0 citationsarXiv
Falcon Perception2603.27365v1 · Aviraj Bevli, Sofian Chaybouti, Yasser Dahou et al.2026 · 0 citationsarXiv
Beyond Microservices: Testing Web-Scale RCA Methods on GPU-Driven LLM Workloads2603.02057v1 · Dominik Scheinert, Alexander Acker, Thorsten Wittkopp et al.2026 · 0 citationsarXiv
ALRM: Agentic LLM for Robotic Manipulation2601.19510v2 · Vitor Gaboardi dos Santos, Ibrahim Khadraoui, Ibrahim Farhat et al.2026 · 1 citationarXiv
WavLink: Compact Audio-Text Embeddings with a Global Whisper Token2601.15118v2 · Gokul Karthik Kumar, Ludovick Lepauloux, Hakim Hacid2026 · 0 citationsarXiv
Learnable Multipliers: Freeing the Scale of Language Model Matrix Layers2601.04890v1 · Maksim Velikanov, Ilyas Chahed, Jingwei Zuo et al.2026 · 0 citationsarXiv
Falcon-H1R: Pushing the Reasoning Frontiers with a Hybrid Model for Efficient Test-Time Scaling2601.02346v1 · Falcon LLM Team, Iheb Chaabane, Puneesh Khanna et al.2026 · 0 citationsarXiv
SigLino: Efficient Multi-Teacher Distillation for Agglomerative Vision Foundation Models2512.20157v2 · Sofian Chaybouti, Sanath Narayan, Yasser Dahou et al.2025 · 0 citationsarXiv
RELOOP: Recursive Retrieval with Multi-Hop Reasoner and Planners for Heterogeneous QA2510.20505v4 · Ruiyi Yang, Hao Xue, Imran Razzak et al.2025 · 0 citationsarXiv
Evaluating Arabic Large Language Models: A Survey of Benchmarks, Methods, and Gaps2510.13430v2 · Ahmed Alzubaidi, Shaikha Alsuwaidi, Basma El Amel Boussaha et al.2025 · 0 citationsarXiv
Competitive Audio-Language Models with Data-Efficient Single-Stage Training on Public Data2509.07526v3 · Gokul Karthik Kumar, Rishabh Saraf, Ludovick Lepauloux et al.2025 · 1 citationarXiv
Falcon-H1: A Family of Hybrid-Head Language Models Redefining Efficiency and Performance2507.22448v1 · Jingwei Zuo, Maksim Velikanov, Ilyas Chahed et al.2025 · 0 citationsarXiv
3LM: Bridging Arabic, STEM, and Code through Benchmarking2507.15850v3 · Basma El Amel Boussaha, Leen AlQadi, Mugariya Farooq et al.2025 · 0 citationsarXiv
Far From Sight, Far From Mind: Inverse Distance Weighting for Graph Federated Recommendation2507.01285v1 · Aymen Rayane Khouas, Mohamed Reda Bouadjenek, Hakim Hacid et al.2025 · 0 citationsarXiv
NeurIPS 2025 E2LM Competition : Early Training Evaluation of Language Models2506.07731v1 · Mouadh Yagoubi, Yasser Dahou, Billel Mokeddem et al.2025 · 0 citationsarXiv
Rolling Ball Optimizer: Learning by ironing out loss landscape wrinkles2505.19527v3 · Mohammed Djameleddine Belgoumri, Mohamed Reda Bouadjenek, Hakim Hacid et al.2025 · 0 citationsarXiv
Divide by Question, Conquer by Agent: SPLIT-RAG with Question-Driven Graph Partitioning2505.13994v3 · Ruiyi Yang, Hao Xue, Imran Razzak et al.2025 · 0 citationsarXiv
Accurate and Diverse LLM Mathematical Reasoning via Automated PRM-Guided GFlowNets2504.19981v3 · Adam Younsi, Ahmed Attia, Abdalgader Abubaker et al.2025 · 0 citationsarXiv
SVLA: A Unified Speech-Vision-Language Assistant with Multimodal Reasoning and Speech Generation2503.24164v2 · Ngoc Dung Huynh, Mohamed Reda Bouadjenek, Imran Razzak et al.2025 · 0 citationsarXiv
Enforcing Consistency and Fairness in Multi-level Hierarchical Classification with a Mask-based Output Layer2503.15566v1 · Shijing Chen, Shoaib Jameel, Mohamed Reda Bouadjenek et al.2025 · 0 citationsarXiv
Leveraging Taxonomy and LLMs for Improved Multimodal Hierarchical Classification2501.06827v1 · Shijing Chen, Mohamed Reda Bouadjenek, Shoaib Jameel et al.2025 · 1 citationarXiv
Visual question answering: from early developments to recent advances -- a survey2501.03939v2 · Ngoc Dung Huynh, Mohamed Reda Bouadjenek, Sunil Aryal et al.2025 · 2 citationsarXiv
SimpsonsVQA: Enhancing Inquiry-Based Learning with a Tailored Dataset2410.22648v1 · Ngoc Dung Huynh, Mohamed Reda Bouadjenek, Sunil Aryal et al.2024 · 0 citationsarXiv
Maximizing the Potential of Synthetic Data: Insights from Random Matrix Theory2410.08942v1 · Aymane El Firdoussi, Mohamed El Amine Seddik, Soufiane Hayou et al.2024 · 0 citationsarXiv
Falcon Mamba: The First Competitive Attention-free 7B Language Model2410.05355v1 · Jingwei Zuo, Maksim Velikanov, Dhia Eddine Rhaiem et al.2024 · 3 citationsarXiv
Alignment with Preference Optimization Is All You Need for LLM Safety2409.07772v1 · Reda Alami, Ali Khalifa Almansoori, Ahmed Alzubaidi et al.2024 · 0 citationsarXiv
Falcon2-11B Technical Report2407.14885v1 · Quentin Malartic, Nilabhra Roy Chowdhury, Ruxandra Cojocaru et al.2024 · 2 citationsarXiv
PORT: Preference Optimization on Reasoning Traces2406.16061v2 · Salem Lahlou, Abdalgader Abubaker, Hakim Hacid2024 · 0 citationsarXiv
Data Quality in Edge Machine Learning: A State-of-the-Art Survey2406.02600v1 · Mohammed Djameleddine Belgoumri, Mohamed Reda Bouadjenek, Sunil Aryal et al.2024 · 3 citationsarXiv
ViSpeR: Multilingual Audio-Visual Speech Recognition2406.00038v1 · Sanath Narayan, Yasser Abdelaziz Dahou Djilali, Ankit Singh et al.2024 · 1 citationarXiv
BayesJudge: Bayesian Kernel Language Modelling with Confidence Uncertainty in Legal Judgment Prediction2404.10481v1 · Ubaid Azam, Imran Razzak, Shelly Vishwakarma et al.2024 · 0 citationsarXiv
From Uncertainty to Trust: Kernel Dropout for AI-Powered Medical Predictions2404.10483v2 · Ubaid Azam, Imran Razzak, Shelly Vishwakarma et al.2024 · 0 citationsarXiv
Training Machine Learning models at the Edge: A Survey2403.02619v3 · Aymen Rayane Khouas, Mohamed Reda Bouadjenek, Hakim Hacid et al.2024 · 12 citationsACM Transactions on Intelligent Systems and Technology, 2026
MAGNETO: Edge AI for Human Activity Recognition -- Privacy and Personalization2402.07180v2 · Jingwei Zuo, George Arvanitakis, Mthandazo Ndhlovu et al.2024 · 0 citationsarXiv
Re-thinking Human Activity Recognition with Hierarchy-aware Label Relationship Modeling2403.05557v1 · Jingwei Zuo, Hakim Hacid2024 · 0 citationsarXiv
Practical Insights on Incremental Learning of New Human Physical Activity on the Edge2308.11691v1 · George Arvanitakis, Jingwei Zuo, Mthandazo Ndhlovu et al.2023 · 1 citationarXiv
Opportunistic Air Quality Monitoring and Forecasting with Expandable Graph Neural Networks2307.15916v1 · Jingwei Zuo, Wenbin Li, Michele Baldo et al.2023 · 1 citationarXiv
Unleashing Realistic Air Quality Forecasting: Introducing the Ready-to-Use PurpleAirSF Dataset2306.13948v2 · Jingwei Zuo, Wenbin Li, Michele Baldo et al.2023 · 2 citationsarXiv
Regularization of the policy updates for stabilizing Mean Field Games2304.01547v2 · Talal Algumaei, Ruben Solozabal, Reda Alami et al.2023 · 0 citationsarXiv
On Handling Catastrophic Forgetting for Incremental Learning of Human Physical Activity on the Edge2302.09310v1 · Jingwei Zuo, George Arvanitakis, Hakim Hacid2023 · 1 citationarXiv
A Comprehensive Review and a Taxonomy of Edge Machine Learning: Requirements, Paradigms, and Techniques2302.08571v2 · Wenbin Li, Hakim Hacid, Ebtesam Almazrouei et al.2023 · 28 citationsarXiv
Predicting the Temporal Dynamics of Information Diffusion in Social Networks1302.5235v2 · Adrien Guille, Hakim Hacid, C'ecile Favre2013 · 17 citationsarXiv
Career total: 178 works. 46 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.