Jannik Brinkmann

6 papers · 2023–2025 · 6 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (15) 🐣 Hot Topic Early Bird 👥 Mega-Team · Squad

Venues

ACL (1) EMNLP (1) ICCV (1) ICLR (1) NAACL (1) NeurIPS (1)

Top co-authors

Christian Bartelt (3) Can Rager (2) Samuel Marks (2) David Bau (2) Paul Swoboda (2) Aaron Mueller (2) Arnab Sen Sharma (1) Rico Angell (1) Victor Levoso (1) Jaden Fried Fiotto-Kaufman (1)

Research topics

Artificial Intelligence (5) Core AI (5) Deep Learning (4) Natural Language Processing (4) Architectures (4) Machine Learning (3) Resources & Methods (3) Core Methods (2) Application Areas (1) Generation (1) Learning Types · Deep Learning (1) Learning Types · Machine Learning (1) Understanding (1)

Keywords

representation learning (2) sparse autoencoder (2) language model (2) symbolic reasoning (1) feature disentanglement (1) foundation model (1) language model interpretability (1) ground truth metric (1) model internal (1) social bia (1) counterfactual augmentation (1) syntactic representation (1) multilingual representation (1) syntactic knowledge (1) large language model (1) neural network (1) board game (1) concept steering (1) verb tense (1) residual space (1)

Papers

Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages NAACL 2025 NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals ICLR 2025 Steering Language Models in Multi-Token Generation: A Case Study on Tense and Aspect EMNLP 2025 A Mechanistic Analysis of a Transformer Trained on a Symbolic Multi-Step Reasoning Task ACL 2024 Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models NeurIPS 2024 A Multidimensional Analysis of Social Biases in Vision Transformers ICCV 2023