Kristian Kersting

Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning ACL 2026 SLR: Automated Synthesis for Scalable Logical Reasoning ACL 2026 Human-in-the-loop or AI-in-the-loop? Automate or Collaborate? AAAI 2025 Judging Quality Across Languages: A Multilingual Approach to Pretraining Data Filtering with Language Models EMNLP 2025 Credibility-Aware Multimodal Fusion Using Probabilistic Circuits AISTATS 2025 STRICTA: Structured Reasoning in Critical Text Assessment for Peer Review and Beyond ACL 2025 Multilingual Text-to-Image Generation Magnifies Gender Stereotypes ACL 2025 ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding ICLR 2025 BlendRL: A Framework for Merging Symbolic and Neural Policy Learning ICLR 2025 Scaling Probabilistic Circuits via Data Partitioning UAI 2025 Bongard in Wonderland: Visual Puzzles that Still Make AI Go Mad? ICML 2025 LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models ICML 2025 Where is the Truth? The Risk of Getting Confounded in a Continual World ICML 2025 Hyperparameter Optimization via Interacting with Probabilistic Circuits AUTOML 2025 ART: Adaptive Relation Tuning for Generalized Relation Prediction ICCV 2025 Systems with Switching Causal Relations: A Meta-Causal Perspective ICLR 2025 METok: Multi-Stage Event-based Token Compression for Efficient Long Video Understanding EMNLP 2025 $Ψ$net: Efficient Causal Modeling at Scale PGM 2024 DeiSAM: Segment Anything with Deictic Prompting NIPS 2024 Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents NIPS 2024 Neural Concept Binder NIPS 2024 Graph Neural Networks Need Cluster-Normalize-Activate Modules NIPS 2024 Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models NIPS 2024 Bi-Level One-Shot Architecture Search for Probabilistic Time Series Forecasting AUTOML 2024 Deep Classifier Mimicry without Data Access AISTATS 2024 LEDITS++: Limitless Image Editing using Text-to-Image Models CVPR 2024 T-FREE: Subword Tokenizer-Free Generative LLMs via Sparse Representations for Memory-Efficient Embeddings EMNLP 2024 Community OSCAR: A Community Effort for Multilingual Web Data EMNLP 2024 Occiglot at WMT24: European Open-source Large Language Models Evaluated on Translation EMNLP 2024 Learning Large DAGs is Harder than you Think: Many Losses are Minimal for the Wrong DAG ICLR 2024 Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks ICLR 2024 Adaptive Rational Activations to Boost Deep Reinforcement Learning ICLR 2024 Mechanistic Design and Scaling of Hybrid Architectures ICML 2024 Learning to Intervene on Concept Bottlenecks ICML 2024 Exploiting Cultural Biases via Homoglyphs inText-to-Image Synthesis (Abstract Reprint) IJCAI 2024 Divergent Token Metrics: Measuring degradation to prune away LLM components – and optimize quantization NAACL 2024 $χ$SPN: Characteristic Interventional Sum-Product Networks for Causal Inference in Hybrid Domains UAI 2024 Pix2Code: Learning to Compose Neural Visual Concepts as Programs UAI 2024 Distilling Adversarial Prompts from Safety Benchmarks: Report for the Adversarial Nibbler Challenge IJCNLP 2023 Distilling Adversarial Prompts from Safety Benchmarks: Report for the Adversarial Nibbler Challenge AACL 2023 Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models CVPR 2023 Probabilistic Flow Circuits: Towards Unified Deep Models for Tractable Probabilistic Inference UAI 2023 ATMAN: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation NIPS 2023 Do Not Marginalize Mechanisms, Rather Consolidate! NIPS 2023 ILLUME: Rationalizing Vision-Language Models through Human Interactions ICML 2023 Probabilistic circuits that know what they don’t know UAI 2023 MultiFusion: Fusing Pre-Trained Models for Multi-Lingual, Multi-Modal Image Generation NIPS 2023 Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstraction NIPS 2023 Characteristic Circuits NIPS 2023 Speaking Multiple Languages Affects the Moral Bias of Language Models ACL 2023 ChatGPT is fun, but it is not funny! Humor is still challenging Large Language Models ACL 2023 SEGA: Instructing Text-to-Image Models using Semantic Guidance NIPS 2023 Rickrolling the Artist: Injecting Backdoors into Text Encoders for Text-to-Image Synthesis ICCV 2023 Vision Relation Transformer for Unbiased Scene Graph Generation ICCV 2023 Explaining Deep Tractable Probabilistic Models: The sum-product network case PGM 2022 Predictive Whittle networks for time series UAI 2022 Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks ICML 2022 Interactive Disentanglement: Learning Concepts by Interacting With Their Prototype Representations CVPR 2022 Neuro-Symbolic Verification of Deep Neural Networks IJCAI 2022 Adaptable Adapters NAACL 2022 To Trust or Not To Trust Prediction Scores for Membership Inference Attacks IJCAI 2022 CLEVA-Compass: A Continual Learning Evaluation Assessment Compass to Promote Research Transparency and Comparability ICLR 2022 Interventional Sum-Product Networks: Causal Inference with Tractable Probabilistic Models NIPS 2021 Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting With Their Explanations CVPR 2021 Right for Better Reasons: Training Differentiable Models by Constraining their Influence Functions AAAI 2021 Whittle Networks: A Deep Likelihood Model for Time Series ICML 2021 Leveraging probabilistic circuits for nonparametric multi-output regression UAI 2021 Padé Activation Units: End-to-end Learning of Flexible Activation Functions in Deep Networks ICLR 2020 Structured Object-Aware Physics Prediction for Video Modeling and Planning ICLR 2020 Einsum Networks: Fast and Scalable Learning of Tractable Probabilistic Circuits ICML 2020 Discriminative Non-Parametric Learning of Arithmetic Circuits PGM 2020 Conditional Sum-Product Networks: Imposing Structure on Deep Probabilistic Architectures PGM 2020 Residual Sum-Product Networks PGM 2020 Fast Relational Probabilistic Inference and Learning: Approximate Counting via Hypergraphs AAAI 2019 Faster Attend-Infer-Repeat with Tractable Probabilistic Models ICML 2019 Automatic Bayesian Density Analysis AAAI 2019 Random Sum-Product Networks: A Simple and Effective Approach to Probabilistic Deep Learning UAI 2019 Lifted Filtering via Exchangeable Decomposition IJCAI 2018 Efficient Symbolic Integration for Probabilistic Inference IJCAI 2018 Systems AI: A Declarative Learning Based Programming Perspective IJCAI 2018 Stochastic Online Anomaly Analysis for Streaming Time Series IJCAI 2017 Learning Using Unselected Features (LUFe) IJCAI 2016 Computer Science on the Move: Inferring Migration Regularities from the Web via Compressed Label Propagation IJCAI 2015 pyGPs -- A Python Library for Gaussian Process Regression and Classification JMLR 2015 Mind the Nuisance: Gaussian Process Classification using Privileged Noise NIPS 2014 Efficient Lifting of MAP LP Relaxations Using k-Locality AISTATS 2014 Coinciding Walk Kernels: Parallel Absorbing Random Walks for Learning with Graphs and Few Labels ACML 2013 Lifted Linear Programming AISTATS 2012 Exploration in Relational Domains for Model-based Reinforcement Learning JMLR 2012 Symbolic Dynamic Programming for Continuous State and Observation POMDPs NIPS 2012 Markov Logic Mixtures of Gaussian Processes: Towards Machines Reading Regression Data AISTATS 2012 Hierarchical Convex NMF for Clustering Massive Data ACML 2010 Gaussian Beam Processes: A Nonparametric Bayesian Measurement Model for Range Finders RSS 2007 Integrating Naïve Bayes and FOIL JMLR 2007