Get started
Author

Jannik Brinkmann

Agents of Chaos
2026 · Shapira, Natalie, Wendler, Chris, et al. · arXiv (Cornell University) · 6
PDF
A Multidimensional Analysis of Social Biases in Vision Transformers
2023 · Jannik Brinkmann, Paul Swoboda, et al. · IEEE/CVF International Conference on Computer Vision (ICCV) · 6
PDF
Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages
2025 · Jannik Brinkmann, Chris Wendler, et al. · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · 4
PDF
NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals
2024 · Fiotto-Kaufman, Jaden, Loftus, Alexander R., et al. · arXiv (Cornell University) · 4
PDF
The Quest for the Right Mediator: Surveying Mechanistic Interpretability for NLP Through the Lens of Causal Mediation Analysis
2025 · Aaron Mueller, Jannik Brinkmann, et al. · Computational Linguistics · 3
PDF
A Mechanistic Analysis of a Transformer Trained on a Symbolic Multi-Step Reasoning Task
2024 · Jannik Brinkmann, Abhay Sheshadri, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · 3
PDF
The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysis
2024 · Mueller, Aaron, Brinkmann, Jannik, et al. · arXiv (Cornell University) · 2
PDF
Two Stages of Folding: Convergent Mechanisms in AI Protein Folding Trunks
2026 · Lu, Kevin, Brinkmann, Jannik, et al. · arXiv (Cornell University) · 1
PDF
NSA: Neuro-symbolic ARC Challenge
2026 · Pawel Batorski, Jannik Brinkmann, et al. · European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN) · 1
PDF
Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models
2024 · Adam Karvonen, Benjamin Wright, et al. · neural information processing systems · 1
Synthetic Persona Pretraining: Alignment from Token Zero
2026 · Minder, Julian, Moskvoretskii, Viktor, et al. · arXiv (Cornell University)
PDF
Mitigating Adaptive Attacks against Reasoning Models with Activation Consistency Training
2026 · Shah, Avidan, Brinkmann, Jannik, et al. · arXiv (Cornell University)
PDF
The Quest for the Right Mediator: Surveying Mechanistic Interpretability for NLP Through the Lens of Causal Mediation Analysis
2026 · Association for Computational Linguistics 2026, Bau, David, et al. · Underline Science Inc.
Agents of Chaos
2026 · Shapira, Natalie, Wendler, Chris, et al.
Mood Matters: How Syntactic Sensitivity Undermines Safety Alignment
2026 · Alina Klerings, Jannik Brinkmann, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
The Interlingua Hypothesis: LLMs Translate via a Latent Task-agnostic Feature Space
2026 · Jacob Brinton, Jannik Brinkmann, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
In-Context Learning Beyond Copying: A Training-Time Analysis of Abstractive ICL
2026 · Kerem Şahin, Sheridan Feucht, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
In-Context Algebra
2025 · Todd, Eric, Brinkmann, Jannik, et al. · arXiv (Cornell University)
PDF
Jailbreak Transferability Emerges from Shared Representations
2025 · Angell, Rico, Brinkmann, Jannik, et al. · arXiv (Cornell University)
PDF
Intermodales Hitchhike-Logistiksystem auf Basis KI-basierter Fahrtendisposition selbstorganisierender Lieferboxen
2025 · Rouwen, Stefan, Pilling, Robin, et al. · RENATE
Steering Language Models in Multi-Token Generation: A Case Study on Tense and Aspect
2025 · Alina Klerings, Jannik Brinkmann, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models
2024 · Karvonen, Adam, Wright, Benjamin, et al. · arXiv (Cornell University)
PDF
GOV-REK: Governed Reward Engineering Kernels for Designing Robust Multi-Agent Reinforcement Learning Systems
2024 · Ashish Rana, Michael Oesterle, et al. · Adaptive Agents and Multi-Agents Systems
GOV-REK: Governed Reward Engineering Kernels for Designing Robust Multi-Agent Reinforcement Learning Systems
2024 · Rana, Ashish, Oesterle, Michael, et al. · arXiv (Cornell University)
PDF
Unsupervised Extraction of Test Scenarios from Time-Series Sensor Data using Trace Graphs
2024 · Jannik Brinkmann, Noah Metzger, et al. · Hawaii International Conference on System Sciences (HICSS)
PDF
Works count: 34
Citation count: 32
H-index: 4
I10-index:
Year
Topic
Type