Kristian Kersting

papers in the register

1. Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning.
   ACL · 2026
2. SLR: Automated Synthesis for Scalable Logical Reasoning.
   ACL · 2026
3. The Constitutional Filter: Bayesian Estimation of Compliant Agents
   IROS · 2025
   Artificial intelligenceComputer scienceMachine learningParticle filter
4. Credibility-Aware Multimodal Fusion Using Probabilistic Circuits.
   AISTATS · 2025
5. METok: Multi-Stage Event-based Token Compression for Efficient Long Video Understanding.
   EMNLP · 2025
6. Probabilistic Mission Design for Neuro-Symbolic Unmanned Aircraft Systems
   IEEE Transactions on Intelligent Transportation Systems · 2025
   Probabilistic logicComputer scienceArtificial intelligence
7. Multilingual Text-to-Image Generation Magnifies Gender Stereotypes.
   ACL · 2025
8. LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models.
   ICML · 2025
9. Scaling Probabilistic Circuits via Data Partitioning.
   UAI · 2025
10. Bongard in Wonderland: Visual Puzzles that Still Make AI Go Mad?
    ICML · 2025
11. BlendRL: A Framework for Merging Symbolic and Neural Policy Learning.
    ICLR · 2025
12. How to Train Your Text-to-Image Model: Evaluating Design Choices for Synthetic Training Captions.
    ICCV · 2025
13. ART: Adaptive Relation Tuning for Generalized Relation Prediction
    ICCV · 2025
    Relation (database)Computer scienceFocus (optics)Artificial intelligence
14. Human-in-the-loop or AI-in-the-loop? Automate or Collaborate?
    AAAI · 2025
    Human-in-the-loopLoop (graph theory)Computer science
15. Where is the Truth? The Risk of Getting Confounded in a Continual World.
    ICML · 2025
16. ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding.
    ICLR · 2025
17. Problem Solving Through Human–AI Preference-based Cooperation
    Computational Linguistics · 2025
    Computer sciencePreferenceArtificial intelligenceCognitive science
18. Core Tokensets for Data-Efficient Sequential Training of Transformers.
    ICCV · 2025
19. Measuring and Guiding Monosemanticity.
    NeurIPS · 2025
20. Systems with Switching Causal Relations: A Meta-Causal Perspective.
    ICLR · 2025
21. STRICTA: Structured Reasoning in Critical Text Assessment for Peer Review and Beyond.
    ACL · 2025
22. Hybrid Many-Objective Optimization in Probabilistic Mission Design for Compliant and Effective UAV Routing
    ACM Journal on Autonomous Transportation Systems · 2025
    Probabilistic logicRouting (electronic design automation)Computer science
23. Judging Quality Across Languages: A Multilingual Approach to Pretraining Data Filtering with Language Models.
    EMNLP · 2025
24. EmoNet-Face: An Expert-Annotated Benchmark for Synthetic Emotion Recognition.
    NeurIPS · 2025
25. Causality in Flux: Continual Adaptation of Causal Knowledge via Evidence Matching.
    AAAI · 2024
26. Auditing and instructing text-to-image generation models on fairness
    AI and Ethics · 2024
    Generative grammarComputer scienceSoftware deploymentImage (mathematics)
27. Towards Probabilistic Clearance, Explanation and Optimization
    2024
    Probabilistic logicComputer science
28. Graph Neural Networks Need Cluster-Normalize-Activate Modules.
    NeurIPS · 2024
29. Exploiting Cultural Biases via Homoglyphs inText-to-Image Synthesis (Abstract Reprint).
    IJCAI · 2024
30. Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks.
    ICLR · 2024
31. LEDITS++: Limitless Image Editing Using Text-to-Image Models
    CVPR · 2024
    Image (mathematics)Computer scienceImage editingArtificial intelligence
32. T-FREE: Subword Tokenizer-Free Generative LLMs via Sparse Representations for Memory-Efficient Embeddings.
    EMNLP · 2024
33. APT: Alarm Prediction Transformer
    Expert Systems with Applications · 2024
    Computer scienceALARMTransformerArtificial intelligence
34. Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models.
    NeurIPS · 2024
35. Effective Risk Detection for Natural Gas Pipelines Using Low-Resolution Satellite Images
    Remote Sensing · 2024
    Pipeline transportComputer sciencePipeline (software)Remote sensing
36. Neural-Symbolic Argumentation Mining: An Argument in Favor of Deep Learning and Reasoning
    TUbilio (Technical University of Darmstadt) · 2024
    Argumentation theoryArgument (complex analysis)Computer scienceArtificial intelligence
37. Learning Large DAGs is Harder than you Think: Many Losses are Minimal for the Wrong DAG.
    ICLR · 2024
38. Divergent Token Metrics: Measuring degradation to prune away LLM components - and optimize quantization.
    NAACL · 2024
39. Pix2Code: Learning to Compose Neural Visual Concepts as Programs.
    UAI · 2024
40. Does CLIP Know My Face?
    Journal of Artificial Intelligence Research · 2024
    Computer scienceInferenceVariety (cybernetics)Identity (music)
41. “Do Not Disturb My Circles!” Identifying the Type of Counterfactual at Hand (Short Paper)
    Lecture notes in computer science · 2024
    Counterfactual thinkingComputer scienceType (biology)Artificial intelligence
42. Adaptive Rational Activations to Boost Deep Reinforcement Learning.
    ICLR · 2024
43. Learning to Intervene on Concept Bottlenecks.
    ICML · 2024
44. Deep Classifier Mimicry without Data Access.
    AISTATS · 2024
45. χSPN: Characteristic Interventional Sum-Product Networks for Causal Inference in Hybrid Domains.
    UAI · 2024
46. Mechanistic Design and Scaling of Hybrid Architectures.
    ICML · 2024
47. Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents.
    NeurIPS · 2024
48. We Should Care about Explaining Even Linear Programs
    2024
    Computer scienceAttributionRelevance (law)Solver
49. Neural Concept Binder.
    NeurIPS · 2024
50. DeiSAM: Segment Anything with Deictic Prompting.
    NeurIPS · 2024
51. Representation Matters for Mastering Chess: Improved Feature Representation in AlphaZero Outperforms Switching to Transformers
    Frontiers in artificial intelligence and applications · 2024
    Representation (politics)TransformerArtificial intelligenceComputer science
52. Structural causal models reveal confounder bias in linear program modelling
    Machine Learning · 2024
    Adversarial systemMathematical proofComputer scienceFormalism (music)
53. Multimodal transformer for early alarm prediction
    Engineering Applications of Artificial Intelligence · 2024
    Computer scienceALARMTransformerArtificial intelligence
54. One Explanation Does Not Fit XIL.
    ICLR · 2023
55. ILLUME: Rationalizing Vision-Language Models through Human Interactions.
    ICML · 2023
56. SEGA: Instructing Text-to-Image Models using Semantic Guidance.
    NeurIPS · 2023
57. Characteristic Circuits.
    NeurIPS · 2023
58. ATMAN: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation.
    NeurIPS · 2023
59. Speaking Multiple Languages Affects the Moral Bias of Language Models.
    ACL · 2023
60. Do Not Marginalize Mechanisms, Rather Consolidate!
    NeurIPS · 2023
61. Rickrolling the Artist: Injecting Backdoors into Text Encoders for Text-to-Image Synthesis.
    ICCV · 2023
62. Probabilistic circuits that know what they don't know.
    UAI · 2023
63. Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models.
    CVPR · 2023
64. Vision Relation Transformer for Unbiased Scene Graph Generation.
    ICCV · 2023
65. MultiFusion: Fusing Pre-Trained Models for Multi-Lingual, Multi-Modal Image Generation.
    NeurIPS · 2023
66. Probabilistic Flow Circuits: Towards Unified Deep Models for Tractable Probabilistic Inference.
    UAI · 2023
67. Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstraction.
    NeurIPS · 2023
68. Never Ending Reasoning and Learning: Opportunities and Challenges.
    AAAI · 2023
69. To Trust or Not To Trust Prediction Scores for Membership Inference Attacks.
    IJCAI · 2022
70. Interactive Disentanglement: Learning Concepts by Interacting with their Prototype Representations.
    CVPR · 2022
71. Adaptable Adapters.
    NAACL · 2022
72. Neuro-Symbolic Verification of Deep Neural Networks.
    IJCAI · 2022
73. CLEVA-Compass: A Continual Learning Evaluation Assessment Compass to Promote Research Transparency and Comparability.
    ICLR · 2022
74. Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks.
    ICML · 2022
75. Predictive Whittle networks for time series.
    UAI · 2022
76. Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting With Their Explanations.
    CVPR · 2021
77. Right for Better Reasons: Training Differentiable Models by Constraining their Influence Functions.
    AAAI · 2021
78. Interventional Sum-Product Networks: Causal Inference with Tractable Probabilistic Models.
    NeurIPS · 2021
79. Leveraging probabilistic circuits for nonparametric multi-output regression.
    UAI · 2021
80. Whittle Networks: A Deep Likelihood Model for Time Series.
    ICML · 2021
81. Structured Object-Aware Physics Prediction for Video Modeling and Planning.
    ICLR · 2020
82. Padé Activation Units: End-to-end Learning of Flexible Activation Functions in Deep Networks.
    ICLR · 2020
83. Einsum Networks: Fast and Scalable Learning of Tractable Probabilistic Circuits.
    ICML · 2020
84. Fast Relational Probabilistic Inference and Learning: Approximate Counting via Hypergraphs.
    AAAI · 2019
85. Faster Attend-Infer-Repeat with Tractable Probabilistic Models.
    ICML · 2019
86. Random Sum-Product Networks: A Simple and Effective Approach to Probabilistic Deep Learning.
    UAI · 2019
87. Automatic Bayesian Density Analysis.
    AAAI · 2019
88. Mixed Sum-Product Networks: A Deep Architecture for Hybrid Domains.
    AAAI · 2018
89. Systems AI: A Declarative Learning Based Programming Perspective.
    IJCAI · 2018
90. Efficient Symbolic Integration for Probabilistic Inference.
    IJCAI · 2018
91. Sum-Product Autoencoding: Encoding and Decoding Representations Using Sum-Product Networks.
    AAAI · 2018
92. Inducing Probabilistic Context-Free Grammars for the Sequencing of Movement Primitives.
    ICRA · 2018
93. Core Dependency Networks.
    AAAI · 2018
94. Lifted Filtering via Exchangeable Decomposition.
    IJCAI · 2018
95. Poisson Sum-Product Networks: A Deep Architecture for Tractable Multivariate Poisson Distributions.
    AAAI · 2017
96. The Symbolic Interior Point Method.
    AAAI · 2017
97. Stochastic Online Anomaly Analysis for Streaming Time Series.
    IJCAI · 2017
98. Lifted Inference for Convex Quadratic Programs.
    AAAI · 2017
99. Learning Continuous-Time Bayesian Networks in Relational Domains: A Non-Parametric Approach.
    AAAI · 2016
100. RELOOP: A Python-Embedded Declarative Language for Relational Optimization.
     AAAI · 2016
101. Learning Using Unselected Features (LUFe).
     IJCAI · 2016
102. Parameterizing the Distance Distribution of Undirected Networks.
     UAI · 2015
103. Computer Science on the Move: Inferring Migration Regularities from the Web via Compressed Label Propagation.
     IJCAI · 2015
104. Equitable Partitions of Concave Free Energies.
     UAI · 2015
105. Lifted Message Passing as Reparametrization of Graphical Models.
     UAI · 2014
106. Power Iterated Color Refinement.
     AAAI · 2014
107. Lifting Relational MAP-LPs using Cluster Signatures.
     AAAI · 2014
108. Lifting Relational MAP-LPs Using Cluster Signatures.
     AAAI · 2014
109. Preface.
     AAAI · 2014
110. A Deeper Empirical Analysis of CBP Algorithm: Grounding Is the Bottleneck.
     AAAI · 2014
111. Mind the Nuisance: Gaussian Process Classification using Privileged Noise.
     NeurIPS · 2014
112. Efficient Lifting of MAP LP Relaxations Using k-Locality.
     AISTATS · 2014
113. Relational Logistic Regression: The Directed Analog of Markov Logic Networks.
     AAAI · 2014
114. Using Commonsense Knowledge to Automatically Create (Noisy) Training Examples from Text.
     AAAI · 2013
115. Preface.
     AAAI · 2013
116. MapReduce Lifting for Belief Propagation.
     AAAI · 2013
117. Reduce and Re-Lift: Bootstrapped Lifted Likelihood Maximization for MAP.
     AAAI · 2013
118. Reduce and Re-Lift: Bootstrapped Lifted Likelihood Maximization for MAP.
     AAAI · 2013
119. Lifted Inference via k-Locality.
     AAAI · 2013
120. Pre-Symptomatic Prediction of Plant Drought Stress Using Dirichlet-Aggregation Regression on Hyperspectral Images.
     AAAI · 2012
121. Symbolic Dynamic Programming for Continuous State and Observation POMDPs.
     NeurIPS · 2012
122. Latent Dirichlet Allocation Uncovers Spectral Characteristics of Drought Stressed Plants.
     UAI · 2012
123. Imitation Learning in Relational Domains: A Functional-Gradient Boosting Approach.
     IJCAI · 2011
124. Multi-Evidence Lifted Message Passing, with Application to PageRank and the Kalman Filter.
     IJCAI · 2011
125. Markov Logic Sets: Towards Lifted Information Retrieval Using PageRank and Label Propagation.
     AAAI · 2011
126. Lifted Message Passing for Satisfiability.
     AAAI · 2010
127. Informed Lifting for Message-Passing.
     AAAI · 2010
128. Learning to hash logistic regression for fast 3D scan point classification.
     IROS · 2010
129. Symbolic Dynamic Programming for First-order POMDPs.
     AAAI · 2010
130. Exploiting Causal Independence in Markov Logic Networks: Combining Undirected and Directed Models.
     AAAI · 2010
131. Counting Belief Propagation.
     UAI · 2009
132. Generalized First Order Decision Diagrams for First Order Markov Decision Processes.
     IJCAI · 2009
133. Multi-Relational Learning with Gaussian Processes.
     IJCAI · 2009
134. Non-parametric policy gradients: a unified treatment of propositional and relational domains.
     ICML · 2008
135. Social Network Mining with Nonparametric Relational Models.
     KDD · 2008
136. Learning predictive terrain models for legged robot locomotion.
     IROS · 2008
137. Lifted Probabilistic Inference with Counting Formulas.
     AAAI · 2008
138. Gaussian Beam Processes: A Nonparametric Bayesian Measurement Model for Range Finders.
     RSS · 2007
139. Most likely heteroscedastic Gaussian process regression.
     ICML · 2007
140. Robust 3D Scan Point Classification using Associative Markov Networks.
     ICRA · 2006
141. Learning Relational Navigation Policies.
     IROS · 2006
142. nFOIL: Integrating Naïve Bayes and FOIL.
     AAAI · 2005
143. Towards Learning Stochastic Logic Programs from Proof-Banks.
     AAAI · 2005
144. "Say EM" for Selecting Probabilistic Models for Logical Sequences.
     UAI · 2005
145. Bellman goes relational.
     ICML · 2004

Profile built from publicly available sources (OpenAlex, arXiv; origin per Art. 14 GDPR). Corrections or removal · aisr@hessian.ai