29 citations · 43 across the 9 of their papers we have counts for
9 papers
ProgResViT: Progressive Resolution and Width for Adaptive Vision Transformers
Ali Hojjat, Janek Haberer, Olaf Landsiedel
Vision Transformers (ViTs) typically process every image using a fixed input resolution and model width, even though many images can be classified with substantially less computati…
Beyond Silicon: Materials, Mechanisms, and Methods for Physical Neural Computing
Stefan Fischer, Nihat Ay, Olaf Landsiedel +4
Physical implementations of neural computation now extend far beyond silicon hardware, encompassing substrates such as memristive devices, photonic circuits, mechanical metamateria…
Slimmable ConvNeXt: Width-Adaptive Inference for Efficient Multi-Device Deployment
Janek Haberer, Jon Eike Wilhelm, Olaf Landsiedel
Deploying vision models across devices with varying resource constraints, or even on a single device where available compute fluctuates due to battery state, thermal throttling, or…
ThinkingViT: Matryoshka Thinking Vision Transformer for Elastic Inference
Ali Hojjat, Janek Haberer, Soren Pirk +1
ViTs deliver SOTA performance, yet their fixed computational budget prevents scalable deployment across heterogeneous hardware. Recent Matryoshka-style Transformer architectures mi…
LimitNet: Progressive, Content-Aware Image Offloading for Extremely Weak Devices & Networks
Ali Hojjat, Janek Haberer, Tayyaba Zainab +1
IoT devices have limited hardware capabilities and are often deployed in remote areas. Consequently, advanced vision models surpass such devices' processing and storage capabilitie…
MCUCoder: Adaptive Bitrate Learned Video Compression for IoT Devices
Ali Hojjat, Janek Haberer, Olaf Landsiedel
The rapid growth of camera-based IoT devices demands the need for efficient video compression, particularly for edge applications where devices face hardware constraints, often wit…
HydraViT: Stacking Heads for a Scalable ViT
Janek Haberer, Ali Hojjat, Olaf Landsiedel
The architecture of Vision Transformers (ViTs), particularly the Multi-head Attention (MHA) mechanism, imposes substantial hardware demands. Deploying ViTs on devices with varying…
ProgDTD: Progressive Learned Image Compression with Double-Tail-Drop Training
Ali Hojjat, Janek Haberer, Olaf Landsiedel
Progressive compression allows images to start loading as low-resolution versions, becoming clearer as more data is received. This increases user experience when, for example, netw…
Quantifying the Re-identification Risk of Event Logs for Process Mining
S. Nuñez von Voigt, S. A. Fahrenkrog-Petersen, D. Janssen +5
Event logs recorded during the execution of business processes constitute a valuable source of information. Applying process mining techniques to them, event logs may reveal the ac…