15.4k citations · 15.8k across the 20 of their papers we have counts for
23 papers
The Key to Going Linear: Analysis-Driven Transformer Linearization
Anna Kuzina, Paul N. Whatmough, Babak Ehteshami Bejnordi
The quadratic cost of causal self-attention severely bottlenecks long-context transformer inference. While numerous post hoc linearization pipelines exist, it is difficult to ident…
Efficient Reasoning on the Edge
Yelysei Bondarenko, Thomas Hehn, Rob Hesselink +15
Large language models (LLMs) with chain-of-thought reasoning achieve state-of-the-art performance across complex problem-solving tasks, but their verbose reasoning traces and large…
KaVa: Latent Reasoning via Compressed KV-Cache Distillation
Anna Kuzina, Maciej Pioro, Paul N. Whatmough +1
Large Language Models (LLMs) excel at multi-step reasoning problems with explicit chain-of-thought (CoT), but verbose traces incur significant computational costs and memory overhe…
Dirichlet-Prior Shaping: Guiding Expert Specialization in Upcycled MoEs
Leyla Mirvakhabova, Babak Ehteshami Bejnordi, Gaurav Kumar +3
Upcycling pre-trained dense models into sparse Mixture-of-Experts (MoEs) efficiently increases model capacity but often suffers from poor expert specialization due to naive weight…
Mixture of Cache-Conditional Experts for Efficient Mobile Device Inference
Andrii Skliar, Ties van Rozendaal, Romain Lepert +5
Mixture of Experts (MoE) LLMs have recently gained attention for their ability to enhance performance by selectively engaging specialized subnetworks or "experts" for each input. H…
Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design
Ruisi Cai, Yeonju Ro, Geon-Woo Kim +4
The proliferation of large language models (LLMs) has led to the adoption of Mixture-of-Experts (MoE) architectures that dynamically leverage specialized subnetworks for improved e…
InterroGate: Learning to Share, Specialize, and Prune Representations for Multi-task Learning
Babak Ehteshami Bejnordi, Gaurav Kumar, Amelie Royer +3
Jointly learning multiple tasks with a unified model can improve accuracy and data efficiency, but it faces the challenge of task interference, where optimizing one task objective…
Think Big, Generate Quick: LLM-to-SLM for Fast Autoregressive Decoding
Benjamin Bergner, Andrii Skliar, Amelie Royer +3
Large language models (LLMs) have become ubiquitous in practice and are widely used for generation tasks such as translation, summarization and instruction following. However, thei…
Scalarization for Multi-Task and Multi-Domain Learning at Scale
Amelie Royer, Tijmen Blankevoort, Babak Ehteshami Bejnordi
Training a single model on multiple input domains and/or output tasks allows for compressing information from multiple sources into a unified backbone hence improves model efficien…
MSViT: Dynamic Mixed-Scale Tokenization for Vision Transformers
Jakob Drachmann Havtorn, Amelie Royer, Tijmen Blankevoort +1
The input tokens to Vision Transformers carry little semantic meaning as they are defined as regular equal-sized patches of the input image, regardless of its content. However, pro…
Revisiting Single-gated Mixtures of Experts
Amelie Royer, Ilia Karmanov, Andrii Skliar +2
Mixture of Experts (MoE) are rising in popularity as a means to train extremely large-scale models, yet allowing for a reasonable computational cost at inference time. Recent state…
Computational Pathology: A Survey Review and The Way Forward
Mahdi S. Hosseini, Babak Ehteshami Bejnordi, Vincent Quoc-Huy Trinh +18
Computational Pathology CPath is an interdisciplinary science that augments developments of computational approaches to analyze and model medical histopathology images. The main ob…
SALISA: Saliency-based Input Sampling for Efficient Video Object Detection
Babak Ehteshami Bejnordi, Amirhossein Habibian, Fatih Porikli +1
High-resolution images are widely adopted for high-performance object detection in videos. However, processing high-resolution inputs comes with high computation costs, and naive d…
FrameExit: Conditional Early Exiting for Efficient Video Recognition
Amir Ghodrati, Babak Ehteshami Bejnordi, Amirhossein Habibian
In this paper, we propose a conditional early exiting framework for efficient video recognition. While existing works focus on selecting a subset of salient frames to reduce the co…
Skip-Convolutions for Efficient Video Processing
Amirhossein Habibian, Davide Abati, Taco S. Cohen +1
We propose Skip-Convolutions to leverage the large amount of redundancies in video streams and save computations. Each video is represented as a series of changes across frames and…
TimeGate: Conditional Gating of Segments in Long-range Activities
Noureldien Hussein, Mihir Jain, Babak Ehteshami Bejnordi
When recognizing a long-range activity, exploring the entire video is exhaustive and computationally expensive, as it can span up to a few minutes. Thus, it is of great importance…
Conditional Channel Gated Networks for Task-Aware Continual Learning
Davide Abati, Jakub Tomczak, Tijmen Blankevoort +3
Convolutional Neural Networks experience catastrophic forgetting when optimized on a sequence of learning problems: as they meet the objective of the current training examples, the…
Batch-Shaping for Learning Conditional Channel Gated Networks
Babak Ehteshami Bejnordi, Tijmen Blankevoort, Max Welling
We present a method that trains large capacity neural networks with significantly improved accuracy and lower dynamic computational cost. We achieve this by gating the deep-learnin…
Predicting breast tumor proliferation from whole-slide images: the TUPAC16 challenge
Mitko Veta, Yujing J. Heng, Nikolas Stathonikos +30
Tumor proliferation is an important biomarker indicative of the prognosis of breast cancer patients. Assessment of tumor proliferation in a clinical setting is highly subjective an…
Context-aware stacked convolutional neural networks for classification of breast carcinomas in whole-slide histopathology images
Babak Ehteshami Bejnordi, Guido Zuidhof, Maschenka Balkenhol +6
Automated classification of histopathological whole-slide images (WSI) of breast tissue requires analysis at very high resolutions with a large contextual area. In this paper, we p…
Deep learning-based assessment of tumor-associated stroma for diagnosing breast cancer in histopathology images
Babak Ehteshami Bejnordi, Jimmy Linz, Ben Glass +6
Diagnosis of breast carcinomas has so far been limited to the morphological interpretation of epithelial cells and the assessment of epithelial tissue architecture. Consequently, m…
The importance of stain normalization in colorectal tissue classification with convolutional networks
Francesco Ciompi, Oscar Geessink, Babak Ehteshami Bejnordi +6
The development of reliable imaging biomarkers for the analysis of colorectal cancer (CRC) in hematoxylin and eosin (H&E) stained histopathology images requires an accurate and rep…
A Survey on Deep Learning in Medical Image Analysis
Geert Litjens, Thijs Kooi, Babak Ehteshami Bejnordi +6
Deep learning algorithms, in particular convolutional networks, have rapidly become a methodology of choice for analyzing medical images. This paper reviews the major deep learning…