23 citations · 26 across the 16 of their papers we have counts for
16 papers
LaMoC: Loss-Aware Modular Compression for LLMs
Mohanad Odema, Jacob Song
Modular compression has enabled considerable parameter reduction in LLMs while preserving strong language understanding and downstream task accuracy. However, existing joint modula…
Understanding Calibration and Truncation Error Propagation in Training-Free Low-Rank Compression for LLMs
Mohanad Odema, Gabrielle De Micheli, Dayin Gou +3
Training-free low-rank compression frameworks have been gaining prominence for LLM compression given their effectiveness in reducing model parameter count while maintaining task-le…
3-Model Speculative Decoding
Sanghyun Byun, Mohanad Odema, Jung Ick Guack +3
Speculative Decoding (SD) accelerates inference in large language models by using a smaller draft model to propose tokens, which are then verified by a larger target model. However…
Unifying Vision-Language Latents for Zero-label Image Caption Enhancement
Sanghyun Byun, Jung Ick Guack, Mohanad Odema +3
Vision-language models (VLMs) achieve remarkable performance through large-scale image-text pretraining. However, their reliance on labeled image datasets limits scalability and le…
APCE: Adaptive Progressive Context Expansion for Long Context Processing
Baisub Lee, Sanghyun Byun, Mohanad Odema +3
Deploying useful Long-Context Transformer Models (LCTMs) requires addressing two key challenges: (1) A growing memory footprint due to quadratic self-attention and linear KV-cache…
Performance Implications of Multi-Chiplet Neural Processing Units on Autonomous Driving Perception
Mohanad Odema, Luke Chen, Hyoukjun Kwon +1
We study the application of emerging chiplet-based Neural Processing Units to accelerate vehicular AI perception workloads in constrained automotive settings. The motivation stems…
SCAR: Scheduling Multi-Model AI Workloads on Heterogeneous Multi-Chiplet Module Accelerators
Mohanad Odema, Luke Chen, Hyoukjun Kwon +1
Emerging multi-model workloads with heavy models like recent large language models significantly increased the compute and memory demands on hardware. To address such increasing de…
Inter-Layer Scheduling Space Exploration for Multi-model Inference on Heterogeneous Chiplets
Mohanad Odema, Hyoukjun Kwon, Mohammad Abdullah Al Faruque
To address increasing compute demand from recent multi-model workloads with heavy models like large language models, we propose to deploy heterogeneous chiplet-based multi-chip mod…
MaGNAS: A Mapping-Aware Graph Neural Architecture Search Framework for Heterogeneous MPSoC Deployment
Mohanad Odema, Halima Bouzidi, Hamza Ouarnoughi +2
Graph Neural Networks (GNNs) are becoming increasingly popular for vision-based applications due to their intrinsic capacity in modeling structural and contextual relations between…
Map-and-Conquer: Energy-Efficient Mapping of Dynamic Neural Nets onto Heterogeneous MPSoCs
Halima Bouzidi, Mohanad Odema, Hamza Ouarnoughi +2
Heterogeneous MPSoCs comprise diverse processing units of varying compute capabilities. To date, the mapping strategies of neural networks (NNs) onto such systems are yet to exploi…
SEO: Safety-Aware Energy Optimization Framework for Multi-Sensor Neural Controllers at the Edge
Mohanad Odema, James Ferlez, Yasser Shoukry +1
Runtime energy management has become quintessential for multi-sensor autonomous systems at the edge for achieving high performance given the platform constraints. Typical for such…
EnergyShield: Provably-Safe Offloading of Neural Network Controllers for Energy Efficiency
Mohanad Odema, James Ferlez, Goli Vaisi +2
To mitigate the high energy demand of Neural Network (NN) based Autonomous Driving Systems (ADSs), we consider the problem of offloading NN controllers from the ADS to nearby edge-…
HADAS: Hardware-Aware Dynamic Neural Architecture Search for Edge Performance Scaling
Halima Bouzidi, Mohanad Odema, Hamza Ouarnoughi +2
Dynamic neural networks (DyNNs) have become viable techniques to enable intelligence on resource-constrained edge devices while maintaining computational efficiency. In many cases,…
Romanus: Robust Task Offloading in Modular Multi-Sensor Autonomous Driving Systems
Luke Chen, Mohanad Odema, Mohammad Abdullah Al Faruque
Due to the high performance and safety requirements of self-driving applications, the complexity of modern autonomous driving systems (ADS) has been growing, instigating the need f…
SAGE: A Split-Architecture Methodology for Efficient End-to-End Autonomous Vehicle Control
Arnav Malawade, Mohanad Odema, Sebastien Lajeunesse-DeGroot +1
Autonomous vehicles (AV) are expected to revolutionize transportation and improve road safety significantly. However, these benefits do not come without cost; AVs require large Dee…
LENS: Layer Distribution Enabled Neural Architecture Search in Edge-Cloud Hierarchies
Mohanad Odema, Nafiul Rashid, Berken Utku Demirel +1
Edge-Cloud hierarchical systems employing intelligence through Deep Neural Networks (DNNs) endure the dilemma of workload distribution within them. Previous solutions proposed to d…