


default search action
Kristian Kersting
Person information
- affiliation: TU Darmstadt, Computer Science Department, Germany
- affiliation: TU Darmstadt, Centre for Cognitive Science, Germany
- affiliation: TU Dortmund, Department of Computer Science, Germany
- affiliation: University of Bonn, Faculty of Agriculture, Germany
- affiliation: Fraunhofer Institute for Intelligent Analysis and Information Systems (IAIS), Sankt Augustin, Germany
- affiliation: Massachusetts Institute of Technology, Computer Science and Artificial Intelligence Laboratory (CSAIL), Cambridge, MA, USA
- affiliation (PhD 2005): University of Freiburg, Machine Learning Laborator, Germany
Refine list

refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2025
- [j81]Nika Strem, Devendra Singh Dhami, Benedikt Schmidt, Kristian Kersting:
Multimodal transformer for early alarm prediction. Eng. Appl. Artif. Intell. 139: 109643 (2025) - [j80]Nika Strem
, Devendra Singh Dhami, Benedikt Schmidt, Benjamin Klöpper, Kristian Kersting
:
APT: Alarm Prediction Transformer. Expert Syst. Appl. 261: 125521 (2025) - [j79]Viktor Pfanschilling, Hikaru Shindo, Devendra Singh Dhami, Kristian Kersting:
NeST: The neuro-symbolic transpiler. Int. J. Approx. Reason. 179: 109369 (2025) - [i186]Simon Kohaut, Benedict Flade, Daniel Ochs, Devendra Singh Dhami, Julian Eggert, Kristian Kersting:
Probabilistic Mission Design in Neuro-Symbolic Systems. CoRR abs/2501.01439 (2025) - 2024
- [j78]Quentin Delfosse, Jannis Blüml, Bjarne Gregori, Sebastian Sztwiertnia, Kristian Kersting:
OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments. RLJ 1: 400-449 (2024) - [j77]Dominik Hintersdorf, Lukas Struppek, Manuel Brack, Felix Friedrich, Patrick Schramowski, Kristian Kersting:
Does CLIP Know My Face? J. Artif. Intell. Res. 80: 1033-1062 (2024) - [j76]Matej Zecevic, Devendra Singh Dhami
, Kristian Kersting:
Structural causal models reveal confounder bias in linear program modelling. Mach. Learn. 113(3): 1329-1349 (2024) - [j75]Hikaru Shindo
, Viktor Pfanschilling, Devendra Singh Dhami, Kristian Kersting:
Learning differentiable logic programs for abstract visual reasoning. Mach. Learn. 113(11): 8533-8584 (2024) - [j74]Daniel Ochs, Karsten Wiertz, Sebastian Bußmann, Kristian Kersting, Devendra Singh Dhami
:
Effective Risk Detection for Natural Gas Pipelines Using Low-Resolution Satellite Images. Remote. Sens. 16(2): 266 (2024) - [c242]Saurabh Mathur, Veerendra P. Gadekar, Rashika Ramola, Peixin Wang, Ramachandran Thiruvengadam, David M. Haas, Shinjini Bhatnagar, Nitya Wadhwa, Garbhini Study Group, Predrag Radivojac, Himanshu Sinha, Kristian Kersting, Sriraam Natarajan:
Modeling Multiple Adverse Pregnancy Outcomes: Learning from Diverse Data Sources. AIME (1) 2024: 293-302 - [c241]Steven Braun, Martin Mundt, Kristian Kersting:
Deep Classifier Mimicry without Data Access. AISTATS 2024: 4762-4770 - [c240]Manuel Brack, Felix Friedrich, Katharina Kornmeier, Linoy Tsaban, Patrick Schramowski, Kristian Kersting, Apolinário Passos:
LEDITS++: Limitless Image Editing Using Text-to-Image Models. CVPR 2024: 8861-8870 - [c239]Dominik Hintersdorf, Lukas Struppek, Daniel Neider, Kristian Kersting:
Defending Our Privacy with Backdoors. ECAI 2024: 1832-1839 - [c238]Johannes Czech
, Jannis Blüml
, Kristian Kersting
, Hedinn Steingrimsson
:
Representation Matters for Mastering Chess: Improved Feature Representation in AlphaZero Outperforms Switching to Transformers. ECAI 2024: 2378-2385 - [c237]Björn Deiseroth, Manuel Brack, Patrick Schramowski, Kristian Kersting, Samuel Weinbach:
T-FREE: Subword Tokenizer-Free Generative LLMs via Sparse Representations for Memory-Efficient Embeddings. EMNLP 2024: 21829-21851 - [c236]Quentin Delfosse, Patrick Schramowski, Martin Mundt, Alejandro Molina, Kristian Kersting:
Adaptive Rational Activations to Boost Deep Reinforcement Learning. ICLR 2024 - [c235]Jonas Seng, Matej Zecevic, Devendra Singh Dhami, Kristian Kersting:
Learning Large DAGs is Harder than you Think: Many Losses are Minimal for the Wrong DAG. ICLR 2024 - [c234]Lukas Struppek, Dominik Hintersdorf, Kristian Kersting:
Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks. ICLR 2024 - [c233]Michael Poli, Armin W. Thomas, Eric Nguyen, Pragaash Ponnusamy, Björn Deiseroth, Kristian Kersting, Taiji Suzuki, Brian Hie, Stefano Ermon, Christopher Ré, Ce Zhang, Stefano Massaroli:
Mechanistic Design and Scaling of Hybrid Architectures. ICML 2024 - [c232]David Steinmann, Wolfgang Stammer, Felix Friedrich, Kristian Kersting:
Learning to Intervene on Concept Bottlenecks. ICML 2024 - [c231]Lukas Struppek, Dominik Hintersdorf, Felix Friedrich, Manuel Brack, Patrick Schramowski, Kristian Kersting:
Exploiting Cultural Biases via Homoglyphs inText-to-Image Synthesis (Abstract Reprint). IJCAI 2024: 8486 - [c230]Björn Deiseroth, Max Meuer, Nikolas Gritsch, Constantin Eichenberg, Patrick Schramowski, Matthias Aßenmacher, Kristian Kersting:
Divergent Token Metrics: Measuring degradation to prune away LLM components - and optimize quantization. NAACL-HLT 2024: 6764-6783 - [c229]Quentin Delfosse, Sebastian Sztwiertnia, Mark Rothermel, Wolfgang Stammer, Kristian Kersting:
Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents. NeurIPS 2024 - [c228]Dominik Hintersdorf, Lukas Struppek, Kristian Kersting, Adam Dziedzic, Franziska Boenisch:
Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models. NeurIPS 2024 - [c227]Hikaru Shindo, Manuel Brack, Gopika Sudhakaran, Devendra Singh Dhami, Patrick Schramowski, Kristian Kersting:
DeiSAM: Segment Anything with Deictic Prompting. NeurIPS 2024 - [c226]Arseny Skryagin, Felix Divo, Mohammad Amin Ali, Devendra Singh Dhami, Kristian Kersting:
Graph Neural Networks Need Cluster-Normalize-Activate Modules. NeurIPS 2024 - [c225]Wolfgang Stammer, Antonia Wüst, David Steinmann, Kristian Kersting:
Neural Concept Binder. NeurIPS 2024 - [c224]Moritz Willig
, Matej Zecevic
, Kristian Kersting
:
"Do Not Disturb My Circles!" Identifying the Type of Counterfactual at Hand (Short Paper). RATIO 2024: 266-275 - [c223]Eleftherios Avramidis, Annika Grützner-Zahn, Manuel Brack, Patrick Schramowski, Pedro Ortiz Suarez, Malte Ostendorff, Fabio Barth, Shushen Manakhimova, Vivien Macketanz, Georg Rehm, Kristian Kersting:
Occiglot at WMT24: European Open-source Large Language Models Evaluated on Translation. WMT 2024: 292-298 - [i185]Quentin Delfosse, Sebastian Sztwiertnia, Wolfgang Stammer, Mark Rothermel, Kristian Kersting:
Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents. CoRR abs/2401.05821 (2024) - [i184]Felix Friedrich, Katharina Hämmerl, Patrick Schramowski, Jindrich Libovický, Kristian Kersting, Alexander Fraser:
Multilingual Text-to-Image Generation Magnifies Gender Stereotypes and Prompt Engineering May Not Help You. CoRR abs/2401.16092 (2024) - [i183]Felix Helfenstein
, Jannis Blüml, Johannes Czech, Kristian Kersting:
Checkmating One, by Using Many: Combining Mixture of Experts with MCTS to Improve in Chess. CoRR abs/2401.16852 (2024) - [i182]Roshni Kamath, Rupert Mitchell, Subarnaduti Paul, Kristian Kersting, Martin Mundt:
BOWLL: A Deceptively Simple Open World Lifelong Learner. CoRR abs/2402.04814 (2024) - [i181]Florian Peter Busch, Roshni Kamath, Rupert Mitchell, Wolfgang Stammer, Kristian Kersting, Martin Mundt:
Where is the Truth? The Risk of Getting Confounded in a Continual World. CoRR abs/2402.06434 (2024) - [i180]Antonia Wüst, Wolfgang Stammer, Quentin Delfosse, Devendra Singh Dhami, Kristian Kersting:
Pix2Code: Learning to Compose Neural Visual Concepts as Programs. CoRR abs/2402.08280 (2024) - [i179]Cedric Derstroff, Jannis Brugger, Jannis Blüml, Mira Mezini, Stefan Kramer, Kristian Kersting:
Amplifying Exploration in Monte-Carlo Tree Search by Focusing on the Unknown. CoRR abs/2402.08511 (2024) - [i178]Lukas Struppek, Minh Hieu Le, Dominik Hintersdorf, Kristian Kersting:
Exploring the Adversarial Capabilities of Large Language Models. CoRR abs/2402.09132 (2024) - [i177]Maurice Kraus, David Steinmann, Antonia Wüst, Andre Kokozinski, Kristian Kersting:
Right on Time: Revising Time Series Models by Constraining their Explanations. CoRR abs/2402.12921 (2024) - [i176]Hikaru Shindo, Manuel Brack, Gopika Sudhakaran, Devendra Singh Dhami, Patrick Schramowski, Kristian Kersting:
DeiSAM: Segment Anything with Deictic Prompting. CoRR abs/2402.14123 (2024) - [i175]Maurice Kraus, Felix Divo, David Steinmann, Devendra Singh Dhami, Kristian Kersting:
United We Pretrain, Divided We Fail! Representation Learning for Time Series by Pretraining on 75 Datasets at Once. CoRR abs/2402.15404 (2024) - [i174]Sahil Sidheekh, Pranuthi Tenali, Saurabh Mathur, Erik Blasch, Kristian Kersting, Sriraam Natarajan:
Credibility-Aware Multi-Modal Fusion Using Probabilistic Circuits. CoRR abs/2403.03281 (2024) - [i173]Michael Poli, Armin W. Thomas, Eric Nguyen, Pragaash Ponnusamy, Björn Deiseroth, Kristian Kersting, Taiji Suzuki, Brian Hie, Stefano Ermon, Christopher Ré, Ce Zhang, Stefano Massaroli:
Mechanistic Design and Scaling of Hybrid Architectures. CoRR abs/2403.17844 (2024) - [i172]Simone Tedeschi, Felix Friedrich, Patrick Schramowski, Kristian Kersting, Roberto Navigli, Huu Nguyen, Bo Li:
ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming. CoRR abs/2404.08676 (2024) - [i171]Hector Kohler, Quentin Delfosse, Riad Akrour, Kristian Kersting, Philippe Preux:
Interpretable and Editable Programmatic Tree Policies for Reinforcement Learning. CoRR abs/2405.14956 (2024) - [i170]Dominik Hintersdorf, Lukas Struppek, Kristian Kersting, Adam Dziedzic, Franziska Boenisch:
Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models. CoRR abs/2406.02366 (2024) - [i169]Simon Kohaut, Benedict Flade, Devendra Singh Dhami, Julian Eggert, Kristian Kersting:
Mission Design for Unmanned Aerial Vehicles using Hybrid Probabilistic Logic Program. CoRR abs/2406.03454 (2024) - [i168]Quentin Delfosse, Jannis Blüml, Bjarne Gregori, Kristian Kersting:
HackAtari: Atari Learning Environments for Robust and Continual Reinforcement Learning. CoRR abs/2406.03997 (2024) - [i167]Lukas Helff, Felix Friedrich, Manuel Brack, Kristian Kersting, Patrick Schramowski:
LLavaGuard: VLM-based Safeguards for Vision Dataset Curation and Safety Assessment. CoRR abs/2406.05113 (2024) - [i166]Jingyuan Sha, Hikaru Shindo, Quentin Delfosse, Kristian Kersting, Devendra Singh Dhami:
EXPIL: Explanatory Predicate Invention for Learning in Games. CoRR abs/2406.06107 (2024) - [i165]Wolfgang Stammer, Antonia Wüst, David Steinmann, Kristian Kersting:
Neural Concept Binder. CoRR abs/2406.09949 (2024) - [i164]Simon Kohaut, Benedict Flade, Devendra Singh Dhami, Julian Eggert, Kristian Kersting:
Towards Probabilistic Clearance, Explanation and Optimization. CoRR abs/2406.15088 (2024) - [i163]Timo Kaufmann, Jannis Blüml, Antonia Wüst, Quentin Delfosse, Kristian Kersting, Eyke Hüllermeier:
OCALM: Object-Centric Assessment with Language Models. CoRR abs/2406.16748 (2024) - [i162]Björn Deiseroth, Manuel Brack, Patrick Schramowski, Kristian Kersting, Samuel Weinbach:
T-FREE: Tokenizer-Free Generative LLMs via Sparse Representations for Memory-Efficient Embeddings. CoRR abs/2406.19223 (2024) - [i161]Subhabrata Dutta, Timo Kaufmann, Goran Glavas, Ivan Habernal, Kristian Kersting, Frauke Kreuter, Mira Mezini, Iryna Gurevych, Eyke Hüllermeier, Hinrich Schütze:
Problem Solving Through Human-AI Preference-Based Cooperation. CoRR abs/2408.07461 (2024) - [i160]Harsh Poonia, Moritz Willig, Zhongjie Yu, Matej Zecevic, Kristian Kersting, Devendra Singh Dhami:
χSPN: Characteristic Interventional Sum-Product Networks for Causal Inference in Hybrid Domains. CoRR abs/2408.07545 (2024) - [i159]Nils Dycke, Matej Zecevic, Ilia Kuznetsov, Beatrix Suess, Kristian Kersting, Iryna Gurevych:
Diagnostic Reasoning in Natural Language: Computational Model and Application. CoRR abs/2409.05367 (2024) - [i158]Subarnaduti Paul, Manuel Brack, Patrick Schramowski, Kristian Kersting, Martin Mundt:
Core Tokensets for Data-efficient Sequential Training of Transformers. CoRR abs/2410.05800 (2024) - [i157]Hikaru Shindo, Quentin Delfosse, Devendra Singh Dhami, Kristian Kersting:
BlendRL: A Framework for Merging Symbolic and Neural Policy Learning. CoRR abs/2410.11689 (2024) - [i156]Moritz Willig, Tim Nelson Tobiasch, Florian Peter Busch, Jonas Seng, Devendra Singh Dhami, Kristian Kersting:
Systems with Switching Causal Relations: A Meta-Causal Perspective. CoRR abs/2410.13054 (2024) - [i155]Nils Grandien, Quentin Delfosse, Kristian Kersting:
Interpretable end-to-end Neurosymbolic Reinforcement Learning agents. CoRR abs/2410.14371 (2024) - [i154]Maurice Kraus, Felix Divo, Devendra Singh Dhami, Kristian Kersting:
xLSTM-Mixer: Multivariate Time Series Forecasting by Mixing via Scalar Memories. CoRR abs/2410.16928 (2024) - [i153]Antonia Wüst, Tim Nelson Tobiasch, Lukas Helff, Devendra Singh Dhami, Constantin A. Rothkopf, Kristian Kersting:
Bongard in Wonderland: Visual Puzzles that Still Make AI Go Mad? CoRR abs/2410.19546 (2024) - [i152]Felix Divo, Eric Endress, Kevin Endler, Kristian Kersting, Devendra Singh Dhami:
Forecasting Company Fundamentals. CoRR abs/2411.05791 (2024) - [i151]Ruben Härle, Felix Friedrich, Manuel Brack, Björn Deiseroth, Patrick Schramowski, Kristian Kersting:
SCAR: Sparse Conditioned Autoencoders for Concept Detection and Steering in LLMs. CoRR abs/2411.07122 (2024) - [i150]Arseny Skryagin, Felix Divo, Mohammad Amin Ali, Devendra Singh Dhami, Kristian Kersting:
Graph Neural Networks Need Cluster-Normalize-Activate Modules. CoRR abs/2412.04064 (2024) - [i149]David Steinmann, Felix Divo, Maurice Kraus, Antonia Wüst, Lukas Struppek, Felix Friedrich, Kristian Kersting:
Navigating Shortcuts, Spurious Correlations, and Confounders: From Origins via Detection to Mitigation. CoRR abs/2412.05152 (2024) - [i148]Sriraam Natarajan, Saurabh Mathur, Sahil Sidheekh, Wolfgang Stammer, Kristian Kersting:
Human-in-the-loop or AI-in-the-loop? Automate or Collaborate? CoRR abs/2412.14232 (2024) - [i147]Arseny Skryagin, Daniel Ochs, Phillip Deibert, Simon Kohaut, Devendra Singh Dhami, Kristian Kersting:
Answer Set Networks: Casting Answer Set Programming into Deep Learning. CoRR abs/2412.14814 (2024) - [i146]Felix Friedrich, Simone Tedeschi, Patrick Schramowski, Manuel Brack, Roberto Navigli, Huu Nguyen, Bo Li, Kristian Kersting:
LLMs Lost in Translation: M-ALERT uncovers Cross-Linguistic Safety Gaps. CoRR abs/2412.15035 (2024) - [i145]Simon Kohaut, Felix Divo, Benedict Flade, Devendra Singh Dhami, Julian Eggert, Kristian Kersting:
The Constitutional Filter. CoRR abs/2412.18347 (2024) - [i144]Simon Kohaut, Benedict Flade, Julian Eggert, Devendra Singh Dhami, Kristian Kersting:
StaR Maps: Unveiling Uncertainty in Geospatial Relations. CoRR abs/2412.18356 (2024) - [i143]Simon Kohaut, Nikolas Hohmann, Sebastian Brulin, Benedict Flade, Julian Eggert, Markus Olhofer, Jürgen Adamy, Devendra Singh Dhami, Kristian Kersting:
Hybrid Many-Objective Optimization in Probabilistic Mission Design for Compliant and Effective UAV Routing. CoRR abs/2412.18514 (2024) - 2023
- [j73]Nicolas Pfeuffer, Lorenz Baum
, Wolfgang Stammer, Benjamin M. Abdel-Karim, Patrick Schramowski, Andreas M. Bucher, Christian Hügel, Gernot Rohde, Kristian Kersting, Oliver Hinz:
Explanatory Interactive Machine Learning. Bus. Inf. Syst. Eng. 65(6): 677-701 (2023) - [j72]Jannis Blüml, Johannes Czech, Kristian Kersting:
AlphaZe∗∗: AlphaZero-like baselines for imperfect information games are surprisingly strong. Frontiers Artif. Intell. 6 (2023) - [j71]Siwen Yan, Phillip Odom, Rahul Pasunuri, Kristian Kersting, Sriraam Natarajan:
Learning with privileged and sensitive information: a gradient-boosting approach. Frontiers Artif. Intell. 6 (2023) - [j70]Arseny Skryagin, Daniel Ochs, Devendra Singh Dhami
, Kristian Kersting:
Scalable Neural-Probabilistic Answer Set Programming. J. Artif. Intell. Res. 78: 579-617 (2023) - [j69]Lukas Struppek, Dominik Hintersdorf, Felix Friedrich, Manuel Brack, Patrick Schramowski, Kristian Kersting:
Exploiting Cultural Biases via Homoglyphs in Text-to-Image Synthesis. J. Artif. Intell. Res. 78: 1017-1068 (2023) - [j68]Hikaru Shindo, Viktor Pfanschilling, Devendra Singh Dhami
, Kristian Kersting:
αILP: thinking visual scenes as differentiable logic programs. Mach. Learn. 112(5): 1465-1497 (2023) - [j67]Felix Friedrich
, Wolfgang Stammer
, Patrick Schramowski
, Kristian Kersting
:
A typology for exploring the mitigation of shortcut behaviour. Nat. Mac. Intell. 5(3): 319-330 (2023) - [j66]Matej Zecevic, Devendra Singh Dhami, Kristian Kersting:
Not All Causal Inference is the Same. Trans. Mach. Learn. Res. 2023 (2023) - [j65]Matej Zecevic, Moritz Willig, Devendra Singh Dhami, Kristian Kersting:
Causal Parrots: Large Language Models May Talk Causality But Are Not Causal. Trans. Mach. Learn. Res. 2023 (2023) - [c222]Sriraam Natarajan, Kristian Kersting:
Never Ending Reasoning and Learning: Opportunities and Challenges. AAAI Bridge Program 2023: 71-74 - [c221]Katharina Hämmerl, Björn Deiseroth, Patrick Schramowski, Jindrich Libovický, Constantin A. Rothkopf, Alexander Fraser, Kristian Kersting:
Speaking Multiple Languages Affects the Moral Bias of Language Models. ACL (Findings) 2023: 2137-2156 - [c220]Nandini Ramanan
, Phillip Odom
, Kristian Kersting
, Sriraam Natarajan
:
Active Feature Acquisition via Human Interaction in Relational domains. COMAD/CODS 2023: 70-78 - [c219]Patrick Schramowski, Manuel Brack, Björn Deiseroth, Kristian Kersting:
Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models. CVPR 2023: 22522-22531 - [c218]Felix Friedrich, Wolfgang Stammer, Patrick Schramowski, Kristian Kersting:
Revision Transformers: Instructing Language Models to Change Their Values. ECAI 2023: 756-763 - [c217]Lukas Struppek, Dominik Hintersdorf, Kristian Kersting:
Rickrolling the Artist: Injecting Backdoors into Text Encoders for Text-to-Image Synthesis. ICCV 2023: 4561-4573 - [c216]Gopika Sudhakaran, Devendra Singh Dhami, Kristian Kersting, Stefan Roth:
Vision Relation Transformer for Unbiased Scene Graph Generation. ICCV 2023: 21825-21836 - [c215]Felix Friedrich, David Steinmann, Kristian Kersting:
One Explanation Does Not Fit XIL. Tiny Papers @ ICLR 2023 - [c214]Manuel Brack, Patrick Schramowski, Björn Deiseroth, Kristian Kersting:
ILLUME: Rationalizing Vision-Language Models through Human Interactions. ICML 2023: 3021-3037 - [c213]Simon Kohaut, Benedict Flade
, Devendra Singh Dhami, Julian Eggert, Kristian Kersting:
Mission Design for Unmanned Aerial Vehicles using Hybrid Probabilistic Logic Programs. ITSC 2023: 1506-1513 - [c212]Jingyuan Sha, Hikaru Shindo, Kristian Kersting, Devendra Singh Dhami:
Neural-Symbolic Predicate Invention: Learning Relational Concepts from Visual Scenes. NeSy 2023: 103-117 - [c211]Zhongjie Yu, Martin Trapp, Kristian Kersting:
Characteristic Circuits. NeurIPS 2023 - [c210]Marco Bellagente, Manuel Brack, Hannah Teufel, Felix Friedrich, Björn Deiseroth, Constantin Eichenberg, Andrew Dai, Robert Baldock, Souradeep Nanda, Koen Oostermeijer, Andrés Felipe Cruz-Salinas, Patrick Schramowski, Kristian Kersting, Samuel Weinbach:
MultiFusion: Fusing Pre-Trained Models for Multi-Lingual, Multi-Modal Image Generation. NeurIPS 2023 - [c209]Manuel Brack, Felix Friedrich, Dominik Hintersdorf, Lukas Struppek, Patrick Schramowski, Kristian Kersting:
SEGA: Instructing Text-to-Image Models using Semantic Guidance. NeurIPS 2023 - [c208]Björn Deiseroth, Mayukh Deb, Samuel Weinbach, Manuel Brack, Patrick Schramowski, Kristian Kersting:
ATMAN: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation. NeurIPS 2023 - [c207]Quentin Delfosse, Hikaru Shindo, Devendra Singh Dhami, Kristian Kersting:
Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstraction. NeurIPS 2023 - [c206]Moritz Willig, Matej Zecevic, Devendra Singh Dhami, Kristian Kersting:
Do Not Marginalize Mechanisms, Rather Consolidate! NeurIPS 2023 - [c205]Quentin Delfosse, Wolfgang Stammer, Thomas Rothenbacher, Dwarak Vittal, Kristian Kersting:
Boosting Object Representation Learning via Motion and Object Continuity. ECML/PKDD (4) 2023: 610-628 - [c204]Sahil Sidheekh, Kristian Kersting, Sriraam Natarajan:
Probabilistic Flow Circuits: Towards Unified Deep Models for Tractable Probabilistic Inference. UAI 2023: 1964-1973 - [c203]Fabrizio Ventola, Steven Braun, Zhongjie Yu, Martin Mundt, Kristian Kersting:
Probabilistic circuits that know what they don't know. UAI 2023: 2157-2167 - [c202]Dominik Hintersdorf
, Lukas Struppek
, Kristian Kersting
:
Balancing Transparency and Risk: An Overview of the Security and Privacy Risks of Open-Source Machine Learning Models. AISoLA (Selected Papers) 2023: 269-283 - [c201]Sophie F. Jentzsch, Kristian Kersting:
ChatGPT is fun, but it is not funny! Humor is still challenging Large Language Models. WASSA@ACL 2023: 325-340 - [i142]Mayukh Deb, Björn Deiseroth, Samuel Weinbach, Patrick Schramowski, Kristian Kersting:
AtMan: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation. CoRR abs/2301.08110 (2023) - [i141]Manuel Brack, Felix Friedrich, Dominik Hintersdorf, Lukas Struppek, Patrick Schramowski, Kristian Kersting:
SEGA: Instructing Diffusion using Semantic Dimensions. CoRR abs/2301.12247 (2023) - [i140]Fabrizio Ventola, Steven Braun, Zhongjie Yu, Martin Mundt, Kristian Kersting:
Probabilistic Circuits That Know What They Don't Know. CoRR abs/2302.06544 (2023) - [i139]Felix Friedrich, Patrick Schramowski, Manuel Brack, Lukas Struppek, Dominik Hintersdorf, Sasha Luccioni, Kristian Kersting:
Fair Diffusion: Instructing Text-to-Image Generation Models on Fairness. CoRR abs/2302.10893 (2023) - [i138]Lukas Struppek, Dominik Hintersdorf, Felix Friedrich, Manuel Brack, Patrick Schramowski, Kristian Kersting:
Image Classifiers Leak Sensitive Attributes About Their Classes. CoRR abs/2303.09289 (2023) - [i137]Felix Friedrich, David Steinmann, Kristian Kersting:
One Explanation Does Not Fit XIL. CoRR abs/2304.07136 (2023) - [i136]Johannes Czech, Jannis Blüml, Kristian Kersting:
Representation Matters: The Game of Chess Poses a Challenge to Vision Transformers. CoRR abs/2304.14918 (2023) - [i135]Jannis Weil, Johannes Czech, Tobias Meuser, Kristian Kersting:
Know your Enemy: Investigating Monte-Carlo Tree Search with Opponent Models in Pommerman. CoRR abs/2305.13206 (2023) - [i134]Marco Bellagente, Manuel Brack, Hannah Teufel, Felix Friedrich, Björn Deiseroth, Constantin Eichenberg, Andrew Dai
, Robert Baldock, Souradeep Nanda, Koen Oostermeijer, Andrés Felipe Cruz-Salinas, Patrick Schramowski, Kristian Kersting, Samuel Weinbach:
MultiFusion: Fusing Pre-Trained Models for Multi-Lingual, Multi-Modal Image Generation. CoRR abs/2305.15296 (2023) - [i133]Manuel Brack, Felix Friedrich, Patrick Schramowski, Kristian Kersting:
Mitigating Inappropriateness in Image Generation: Can there be Value in Reflecting the World's Ugliness? CoRR abs/2305.18398 (2023) - [i132]Quentin Delfosse, Hikaru Shindo, Devendra Singh Dhami, Kristian Kersting:
Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstraction. CoRR abs/2306.01439 (2023) - [i131]Steven Braun, Martin Mundt, Kristian Kersting:
Deep Classifier Mimicry without Data Access. CoRR abs/2306.02090 (2023) - [i130]Subarnaduti Paul, Lars-Joel Frey, Roshni Kamath, Kristian Kersting, Martin Mundt:
Masked Autoencoders are Efficient Continual Federated Learners. CoRR abs/2306.03542 (2023) - [i129]Sophie F. Jentzsch, Kristian Kersting:
ChatGPT is fun, but it is not funny! Humor is still challenging Large Language Models. CoRR abs/2306.04563 (2023) - [i128]