Scholar
Andreas Plesner
Google Scholar ID: VyBLS4kAAAAJ
PhD Student, ETH Zurich
Machine learning
Machine Intelligence
Adversarial ML
GPU processing
Fast ML
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
63
H-index
4
i10-index
1
Publications
20
Co-authors
17
list available
Contact
Email
yahya.jabary@gmail.com
LinkedIn
Open ↗
Publications
16 items
A Cheap Verifier is Good Enough: LLM Post-training is Robust to Erroneous Rewards
2026
Cited
0
StudentBench: AI and human tutoring yield equivalent GRE learning gains
2026
Cited
0
GraphARC: A Comprehensive Benchmark for Graph-Based Abstract Reasoning
2026
Cited
0
An Imperfect Verifier is Good Enough: Learning with Noisy Rewards
2026
Cited
0
BitLogic: Training Framework for Gradient-Based FPGA-Native Neural Networks
2026
Cited
0
The Impact of Scaling Training Data on Adversarial Robustness
2025
Cited
0
From MNIST to ImageNet: Understanding the Scalability Boundaries of Differentiable Logic Gate Networks
2025
Cited
0
The Unwinnable Arms Race of AI Image Detection
2025
Cited
0
Load more
Resume
Academic Achievements
Published numerous papers across a wide range of conferences such as NeurIPS, ReliableML@NeurIPS, FoRLM@NeurIPS, and more.
Research Experience
Involved in multiple research projects, including but not limited to:
- Mind the Gap: Removing the Discretization Gap in Differentiable Logic Gate Networks
- The Impact of Scaling Training Data on Adversarial Robustness
- Keep It Real: Challenges in Attacking Compression-Based Adversarial Purification
- GraphARC: A Comprehensive Benchmark for Graph-Based Abstract Reasoning
- The Unwinnable Arms Race of AI Image Detection
- Recurrent Deep Differentiable Logic Gate Networks
- Universality Frontier for Asynchronous Cellular Automata
- ACORD: An Expert-Annotated Retrieval Dataset for Legal Contract Drafting
- Human Aligned Compression for Robust Models
- Synthetic Data for Blood Vessel Network Extraction
- Flip Reasoning Challenge
- Lending in Financial Networks
- Detecting Railway Track Irregularities Using Conformal Prediction
- Breaking reCAPTCHAv2
Background
Member of the Distributed Computing Group; Computer Engineering and Networks Laboratory (TIK); Department of Electrical Engineering (D-ITET)
Co-authors
11 total
Roger Wattenhofer
ETH Zurich
Till Aczel
ETH Zurich
Allan Peter Engsig-Karup
Professor, Scientific Computing
Maksim Zubkov
EPFL
Steven H. Wang
ETH Zürich
Beni Egressy
PhD Student, ETH Zurich
Søren Hauberg
Cognitive Systems, DTU Compute, Technical University of Denmark
Matthew Cook
University of Groningen, Faculty of Science and Engineering & CogniGron Centre