Maksym Andriushchenko
- Papers
- 18
Cite
Notes
Only stored in your browser.
Authored papers
18FutureSim: Replaying World Events to Evaluate Adaptive Agents
arXiv 2026
HalluHard: A Hard Multi-Turn Hallucination Benchmark
arXiv 2026
OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents
arXiv 2025
Monitoring Decomposition Attacks in LLMs with Lightweight Sequential Monitors
arXiv 2025
Capability-Based Scaling Laws for LLM Red-Teaming
arXiv 2025
JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
arXiv 2024
Improving Alignment and Robustness with Circuit Breakers
arXiv 2024
Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs
arXiv 2024
Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks
arXiv 2024
Does Refusal Training in LLMs Generalize to the Past Tense?
arXiv 2024
Is In-Context Learning Sufficient for Instruction Following in LLMs?
arXiv 2024
Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning
arXiv 2024
AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
arXiv 2024
Why Do We Need Weight Decay in Modern Deep Learning?
arXiv 2023
Transferable Adversarial Robustness for Categorical Data via Universal Robust Embeddings
transferable-adversarial-robustness-for
A Modern Look at the Relationship between Sharpness and Generalization
arXiv 2023
Layer-wise Linear Mode Connectivity
arXiv 2023
SGD with Large Step Sizes Learns Sparse Features
arXiv 2022
Affiliations
Frequent co-authors
10from 18 papers