75 citations · 394 across the 149 of their papers we have counts for
37 papers · 1 filter
Beyond Pairwise Correlations: Higher-Order Redundancies in Self-Supervised Representation Learning
David Zollikofer, Béni Egressy, Frederik Benzing +2
Several self-supervised learning (SSL) approaches have shown that redundancy reduction in the feature embedding space is an effective tool for representation learning. However, the…
Towards Learning to Reason: Comparing LLMs with Neuro-Symbolic on Arithmetic Relations in Abstract Reasoning
Michael Hersche, Giacomo Camposampiero, Roger Wattenhofer +2
This work compares large language models (LLMs) and neuro-symbolic approaches in solving Raven's progressive matrices (RPM), a visual abstract reasoning test that involves the unde…
FedRLHF: A Convergence-Guaranteed Federated Framework for Privacy-Preserving and Personalized RLHF
Flint Xiaofeng Fan, Cheston Tan, Yew-Soon Ong +2
In the era of increasing privacy concerns and demand for personalized experiences, traditional Reinforcement Learning with Human Feedback (RLHF) frameworks face significant challen…
Audio Atlas: Visualizing and Exploring Audio Datasets
Luca A. Lanzendörfer, Florian Grötschla, Uzeyir Valizada +1
We introduce Audio Atlas, an interactive web application for visualizing audio data using text-audio embeddings. Audio Atlas is designed to facilitate the exploration and analysis…
Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies
Frédéric Berdoz, Roger Wattenhofer
While autonomous agents often surpass humans in their ability to handle vast and complex data, their potential misalignment (i.e., lack of transparency regarding their true objecti…
Benchmarking Positional Encodings for GNNs and Graph Transformers
Florian Grötschla, Jiaqing Xie, Roger Wattenhofer
Positional Encodings (PEs) are essential for injecting structural information into Graph Neural Networks (GNNs), particularly Graph Transformers, yet their empirical impact remains…
Tiny Transformers Excel at Sentence Compression
Peter Belcak, Roger Wattenhofer
It is staggering that words of the English language, which are on average represented by 5--6 bytes of ASCII, require as much as 24 kilobytes when served to large language models.…
Validity in Network-Agnostic Byzantine Agreement
Andrei Constantinescu, Marc Dufay, Diana Ghinea +1
Byzantine Agreement (BA) considers a setting of parties, out of which up to can exhibit byzantine (malicious) behavior. Honest parties must decide on a common value (agreem…
Conditional Hallucinations for Image Compression
Till Aczel, Roger Wattenhofer
In lossy image compression, models face the challenge of either hallucinating details or generating out-of-distribution samples due to the information bottleneck. This implies that…
ExGra-Med: Extended Context Graph Alignment for Medical Vision-Language Models
Duy M. H. Nguyen, Nghiem T. Diep, Trung Q. Nguyen +10
State-of-the-art medical multi-modal LLMs (med-MLLMs), such as LLaVA-Med and BioMedGPT, primarily depend on scaling model size and data volume, with training driven largely by auto…
On the Lifecycle of a Lightning Network Payment Channel
Florian Grötschla, Lioba Heimbach, Severin Richner +1
The Bitcoin Lightning Network, launched in 2018, serves as a layer 2 scaling solution for Bitcoin. The Lightning Network allows users to establish channels between each other and s…
Towards Leveraging Contrastively Pretrained Neural Audio Embeddings for Recommender Tasks
Florian Grötschla, Luca Strässle, Luca A. Lanzendörfer +1
Music recommender systems frequently utilize network-based models to capture relationships between music pieces, artists, and users. Although these relationships provide valuable i…
Breaking reCAPTCHAv2
Andreas Plesner, Tobias Vontobel, Roger Wattenhofer
Our work examines the efficacy of employing advanced machine learning methods to solve captchas from Google's reCAPTCHAv2 system. We evaluate the effectiveness of automated systems…
Sybil Detection using Graph Neural Networks
Stuart Heeb, Andreas Plesner, Roger Wattenhofer
This paper presents SYBILGAT, a novel approach to Sybil detection in social networks using Graph Attention Networks (GATs). Traditional methods for Sybil detection primarily levera…
Seeing Through the Mask: Rethinking Adversarial Examples for CAPTCHAs
Yahya Jabary, Andreas Plesner, Turlan Kuzhagaliyev +1
Modern CAPTCHAs rely heavily on vision tasks that are supposedly hard for computers but easy for humans. However, advances in image recognition models pose a significant threat to…
Tyche: Collateral-Free Coalition-Resistant Multiparty Lotteries with Arbitrary Payouts
Quentin Kniep, Roger Wattenhofer
We propose Tyche, a family of protocols for performing practically (as well as asymptotically) efficient multiparty lotteries, resistant against aborts and majority coalitions. Our…
Quantifying Liveness and Safety of Avalanche's Snowball
Quentin Kniep, Maxime Laval, Jakub Sliwinski +1
This work examines the resilience properties of the Snowball and Avalanche protocols that underlie the popular Avalanche blockchain. We experimentally quantify the resilience of Sn…
Deanonymizing Ethereum Validators: The P2P Network Has a Privacy Issue
Lioba Heimbach, Yann Vonlanthen, Juan Villacis +2
Many blockchain networks aim to preserve the anonymity of validators in the peer-to-peer (P2P) network, ensuring that no adversary can link a validator's identifier to the IP addre…
GraphFSA: A Finite State Automaton Framework for Algorithmic Learning on Graphs
Florian Grötschla, Joël Mathys, Christoffer Raun +1
Many graph algorithms can be viewed as sets of rules that are iteratively applied, with the number of iterations dependent on the size and complexity of the input graph. Existing m…
AEye: A Visualization Tool for Image Datasets
Florian Grötschla, Luca A. Lanzendörfer, Marco Calzavara +1
Image datasets serve as the foundation for machine learning models in computer vision, significantly influencing model capabilities, performance, and biases alongside architectural…
Asynchronous Approximate Agreement with Quadratic Communication
Mose Mizrahi Erbes, Roger Wattenhofer
We consider an asynchronous network of message-sending parties, up to of which are byzantine. We study approximate agreement, where the parties obtain approximately equal o…
Graph Dimension Attention Networks for Enterprise Credit Assessment
Shaopeng Wei, Beni Egressy, Xingyan Chen +4
Enterprise credit assessment is critical for evaluating financial risk, and Graph Neural Networks (GNNs), with their advanced capability to model inter-entity relationships, are a…
Cue Point Estimation using Object Detection
Giulia Argüello, Luca A. Lanzendörfer, Roger Wattenhofer
Cue points indicate possible temporal boundaries in a transition between two pieces of music in DJ mixing and constitute a crucial element in autonomous DJ systems as well as for l…
Benchmarking GNNs Using Lightning Network Data
Rainer Feichtinger, Florian Grötschla, Lioba Heimbach +1
The Bitcoin Lightning Network is a layer 2 protocol designed to facilitate fast and inexpensive Bitcoin transactions. It operates by establishing channels between users, where Bitc…