42 citations · 77 across the 13 of their papers we have counts for
14 papers
Programming AMD XDNA NPUs with Open-source Compiler Tools: A FlashAttention Case Study
Erwei Wang, Ephrem Wu, Victor J. B. Jung +4
Spatial NPUs such as AMD XDNA place compute tiles beside small local memories and leave data movement between them to software. Mapping a multi-stage workload onto such a device is…
STEEL: Sparsity-Aware Fused Attention for Energy-Efficient Long-Sequence Inference on AMD's XDNA NPU
Victor J. B. Jung, Gagandeep Singh, Joseph Melber +3
The growing adoption of large language model-based agents within operating system workflows has increased the importance of energy-efficient inference on laptop-class systems-on-ch…
BioTrain: Sub-MB, Sub-50mW On-Device Fine-Tuning for Edge-AI on Biosignals
Run Wang, Victor J. B. Jung, Philip Wiese +5
Biosignals exhibit substantial cross-subject and cross-session variability, inducing severe domain shifts that degrade post-deployment performance for small, edge-oriented AI model…
TrainDeeploy: Hardware-Accelerated Parameter-Efficient Fine-Tuning of Small Transformer Models at the Extreme Edge
Run Wang, Victor J. B. Jung, Philip Wiese +3
On-device tuning of deep neural networks enables long-term adaptation at the edge while preserving data privacy. However, the high computational and memory demands of backpropagati…
A Dynamic Allocation Scheme for Adaptive Shared-Memory Mapping on Kilo-core RV Clusters for Attention-Based Model Deployment
Bowen Wang, Marco Bertuletti, Yichao Zhang +2
Attention-based models demand flexible hardware to manage diverse kernels with varying arithmetic intensities and memory access patterns. Large clusters with shared L1 memory, a co…
Fused-Tiled Layers: Minimizing Data Movement on RISC-V SoCs with Software-Managed Caches
Victor J. B. Jung, Alessio Burrello, Francesco Conti +1
The success of DNNs and their high computational requirements pushed for large codesign efforts aiming at DNN acceleration. Since DNNs can be represented as static computational gr…
Distributed Inference with Minimal Off-Chip Traffic for Transformers on Low-Power MCUs
Severin Bochem, Victor J. B. Jung, Arpan Prasad +2
Contextual Artificial Intelligence (AI) based on emerging Transformer models is predicted to drive the next technology revolution in interactive wearable devices such as new-genera…
Deeploy: Enabling Energy-Efficient Deployment of Small Language Models On Heterogeneous Microcontrollers
Moritz Scherer, Luka Macan, Victor Jung +5
With the rise of Embodied Foundation Models (EFMs), most notably Small Language Models (SLMs), adapting Transformers for edge applications has become a very active field of researc…
Toward Attention-based TinyML: A Heterogeneous Accelerated Architecture and Automated Deployment Flow
Philip Wiese, Gamze İslamoğlu, Moritz Scherer +5
One of the challenges for Tiny Machine Learning (tinyML) is keeping up with the evolution of Machine Learning models from Convolutional Neural Networks to Transformers. We address…
Optimizing Layer-Fused Scheduling of Transformer Networks on Multi-accelerator Platforms
Steven Colleman, Arne Symons, Victor J. B. Jung +1
The impact of transformer networks is booming, yet, they come with significant computational complexity. It is therefore essential to understand how to optimally map and execute th…
Optimizing the Deployment of Tiny Transformers on Low-Power MCUs
Victor J. B. Jung, Alessio Burrello, Moritz Scherer +2
Transformer networks are rapidly becoming SotA in many fields, such as NLP and CV. Similarly to CNN, there is a strong push for deploying Transformer models at the extreme edge, ul…
A Tiny Transformer for Low-Power Arrhythmia Classification on Microcontrollers
Paola Busia, Matteo Antonio Scrugli, Victor Jean-Baptiste Jung +2
Wearable systems for the continuous and real-time monitoring of cardiovascular diseases are becoming widespread and valuable assets in diagnosis and therapy. A promising approach f…
ITA: An Energy-Efficient Attention and Softmax Accelerator for Quantized Transformers
Gamze İslamoğlu, Moritz Scherer, Gianna Paulin +4
Transformer networks have emerged as the state-of-the-art approach for natural language processing tasks and are gaining popularity in other domains such as computer vision and aud…
SALSA: Simulated Annealing based Loop-Ordering Scheduler for DNN Accelerators
Victor J. B. Jung, Arne Symons, Linyan Mei +2
To meet the growing need for computational power for DNNs, multiple specialized hardware architectures have been proposed. Each DNN layer should be mapped onto the hardware with th…