17 citations · 18 across the 19 of their papers we have counts for
20 papers
A Cheap Verifier is Good Enough: LLM Post-training is Robust to Erroneous Rewards
Andreas Plesner, Curtis Northcutt, Francisco Guzmán +1
When post-training large language models on tasks with semi-verifiable rewards, there are many factors (training steps, base model size, training order, data quality, verifier accu…
StudentBench: AI and human tutoring yield equivalent GRE learning gains
Curtis Northcutt, Inaara Hasmani, Kevin Feng +3
Artificial intelligence offers an unprecedented opportunity to augment human capabilities, yet progress at the frontier has focused primarily on advancing model capabilities. We in…
GraphARC: A Comprehensive Benchmark for Graph-Based Abstract Reasoning
Saku Peltonen, August Bøgh Rønberg, Andreas Plesner +1
Relational reasoning lies at the heart of intelligence, but existing benchmarks are typically confined to formats such as grids or text. We introduce GraphARC, a benchmark for abst…
An Imperfect Verifier is Good Enough: Learning with Noisy Rewards
Andreas Plesner, Francisco Guzmán, Anish Athalye
Reinforcement Learning with Verifiable Rewards (RLVR) is widely used for post-training Large Language Models, but practical verifiers can make errors. We study how the rate and str…
BitLogic: Training Framework for Gradient-Based FPGA-Native Neural Networks
Simon Bührer, Andreas Plesner, Aczel Till +1
Gradient-based LUT- and logic-gate-based neural networks (LUTNet, LogicNets, DiffLogic, PolyLUT, NeuraLUT, WARP-LUT, DWN, LILogicNet, LightLUT) replace multiply-accumulate arithmet…
GIC-DLC: Differentiable Logic Circuits for Hardware-Friendly Grayscale Image Compression
Till Aczel, David F. Jenny, Simon Bührer +3
Neural image codecs achieve higher compression ratios than traditional hand-crafted methods such as PNG or JPEG-XL, but often incur substantial computational overhead, limiting the…
From MNIST to ImageNet: Understanding the Scalability Boundaries of Differentiable Logic Gate Networks
Sven Brändle, Till Aczel, Andreas Plesner +1
Differentiable Logic Gate Networks (DLGNs) are a very fast and energy-efficient alternative to conventional feed-forward networks. With learnable combinations of logical gates, DLG…
The Impact of Scaling Training Data on Adversarial Robustness
Marco Zimmerli, Andreas Plesner, Till Aczel +1
Deep neural networks remain vulnerable to adversarial examples despite advances in architectures and training paradigms. We investigate how training data characteristics affect adv…
Light Differentiable Logic Gate Networks
Lukas Rüttgers, Till Aczel, Andreas Plesner +1
Differentiable logic gate networks (DLGNs) exhibit extraordinary efficiency at inference while sustaining competitive accuracy. But vanishing gradients, discretization errors, and…
The Unwinnable Arms Race of AI Image Detection
Till Aczel, Lorenzo Vettor, Andreas Plesner +1
The rapid progress of image generative AI has blurred the boundary between synthetic and real images, fueling an arms race between generators and discriminators. This paper investi…
Recurrent Deep Differentiable Logic Gate Networks
Simon Bührer, Andreas Plesner, Till Aczel +1
While differentiable logic gates have shown promise in feedforward networks, their application to sequential modeling remains unexplored. This paper presents the first implementati…
Keep It Real: Challenges in Attacking Compression-Based Adversarial Purification
Samuel Räber, Till Aczel, Andreas Plesner +1
Previous work has suggested that preprocessing images through lossy compression can defend against adversarial perturbations, but comprehensive attack evaluations have been lacking…
FLIP Reasoning Challenge
Andreas Plesner, Turlan Kuzhagaliyev, Roger Wattenhofer
Over the past years, advances in artificial intelligence (AI) have demonstrated how AI can solve many perception and generation tasks, such as image classification and text writing…
Human Aligned Compression for Robust Models
Samuel Räber, Andreas Plesner, Till Aczel +1
Adversarial attacks on image models threaten system robustness by introducing imperceptible perturbations that cause incorrect predictions. We investigate human-aligned learned los…
Synthetic Data for Blood Vessel Network Extraction
Joël Mathys, Andreas Plesner, Jorel Elmiger +1
Blood vessel networks in the brain play a crucial role in stroke research, where understanding their topology is essential for analyzing blood flow dynamics. However, extracting de…
Universality Frontier for Asynchronous Cellular Automata
Ivan Baburin, Matthew Cook, Florian Grötschla +2
In this work, we investigate the computational aspects of asynchronous cellular automata (ACAs), a modification of cellular automata in which cells update independently, following…
ACORD: An Expert-Annotated Retrieval Dataset for Legal Contract Drafting
Steven H. Wang, Maksim Zubkov, Kexin Fan +5
Information retrieval, specifically contract clause retrieval, is foundational to contract drafting because lawyers rarely draft contracts from scratch; instead, they locate and re…
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…