30 citations · 44 across the 12 of their papers we have counts for
13 papers
PPAD-Completeness of Contiguous Envy-Free Cake Cutting with Additive Valuations
Yasushi Kawase, Bodhayan Roy, Mohammad Azharuddin Sanpui
We prove that computing a complete contiguous -envy-free cake allocation is PPAD-complete for normalized rational piecewise-constant additive valuations. The hardness…
Zero-Shot Object Removal via Attention Masking, Latent Anchoring, and Refinement
Arman Taghizadeh, Ulf Krumnack, Kai-Uwe Kühnberger
Removing an object from a real image requires more than synthesizing plausible content within a mask: the method must suppress residual object features, preserve the unedited scene…
Enhancing SLM via ChatGPT and Dataset Augmentation
Tom Pieper, Mohamad Ballout, Ulf Krumnack +2
This paper explores the enhancement of small language models through strategic dataset augmentation via ChatGPT-3.5-Turbo, in the domain of Natural Language Inference (NLI). By emp…
Efficient Knowledge Distillation: Empowering Small Language Models with Teacher Model Insights
Mohamad Ballout, Ulf Krumnack, Gunther Heidemann +1
Enhancing small language models for real-life application deployment is a significant challenge facing the research community. Due to the difficulties and costs of using large lang…
Learning Disentangled Audio Representations through Controlled Synthesis
Yusuf Brima, Ulf Krumnack, Simone Pika +1
This paper tackles the scarcity of benchmarking data in disentangled auditory representation learning. We introduce SynTone, a synthetic dataset with explicit ground truth explanat…
Show Me How It's Done: The Role of Explanations in Fine-Tuning Language Models
Mohamad Ballout, Ulf Krumnack, Gunther Heidemann +1
Our research demonstrates the significant benefits of using fine-tuning with explanations to enhance the performance of language models. Unlike prompting, which maintains the model…
Learning Disentangled Speech Representations
Yusuf Brima, Ulf Krumnack, Simone Pika +1
Disentangled representation learning in speech processing has lagged behind other domains, largely due to the lack of datasets with annotated generative factors for robust evaluati…
Understanding Self-Supervised Learning of Speech Representation via Invariance and Redundancy Reduction
Yusuf Brima, Ulf Krumnack, Simone Pika +1
Self-supervised learning (SSL) has emerged as a promising paradigm for learning flexible speech representations from unlabeled data. By designing pretext tasks that exploit statist…
Investigating Pre-trained Language Models on Cross-Domain Datasets, a Step Closer to General AI
Mohamad Ballout, Ulf Krumnack, Gunther Heidemann +1
Pre-trained language models have recently emerged as a powerful tool for fine-tuning a variety of language tasks. Ideally, when models are pre-trained on large amount of data, they…
Opening the Black Box: Analyzing Attention Weights and Hidden States in Pre-trained Language Models for Non-language Tasks
Mohamad Ballout, Ulf Krumnack, Gunther Heidemann +1
Investigating deep learning language models has always been a significant research area due to the ``black box" nature of most advanced models. With the recent advancements in pre-…
Should You Go Deeper? Optimizing Convolutional Neural Network Architectures without Training by Receptive Field Analysis
Mats L. Richter, Julius Schöning, Anna Wiedenroth +1
When optimizing convolutional neural networks (CNN) for a specific image-based task, specialists commonly overshoot the number of convolutional layers in their designs. By implicat…
Exploring the Properties and Evolution of Neural Network Eigenspaces during Training
Mats L. Richter, Leila Malihi, Anne-Kathrin Patricia Windler +1
In this work we explore the information processing inside neural networks using logistic regression probes \cite{probes} and the saturation metric \cite{featurespace_saturation}. W…
Size Matters
Mats L. Richter, Wolf Byttner, Ulf Krumnack +2
Fully convolutional neural networks can process input of arbitrary size by applying a combination of downsampling and pooling. However, we find that fully convolutional image class…