Kristian Kersting

Full Professor@German Research Center for AI·德国·OpenReview

研究方向

neural-symbolic AI · deep learning · matrix factorization · graph kernels · statistical relational artificial intelligence · probabilistic programming · statistical relational learning · graphical models

Kristian Kersting

Gestalt Reasoning Machines: Structured Perception for Neuro-Symbolic Inference

Chronoberg: Capturing Language Evolution And Temporal Awareness In Foundation Models

ActivationReasoning: Logical Reasoning in Latent Activation Spaces

Neural Concept Verifier: Scaling Prover-Verifier Games via Concept Encodings

From Objects to Skills: Interpretable Meta-Policies for Neural Control

$LIME$: Making LLM Data More Efficient with Linguistic Metadata Embeddings

Finding Dori: Memorization in Text-to-Image Diffusion Models Is Not Local

CausalSteward: An Agentic Divide-Conquer-Combine Copilot for Causal Discovery

Learning from Less: Guiding Deep Reinforcement Learning with Differentiable Symbolic Planning

EmoNet-Voice: A Large-Scale Synthetic Benchmark for Fine-Grained Speech Emotion

Plug-and-Play Object-Centric Reinforcement Learning via Masking

Measuring and Guiding Monosemanticity

Systems with Switching Causal Relations: A Meta-Causal Perspective

xLSTM-Mixer: Multivariate Time Series Forecasting by Mixing via Scalar Memories

BlendRL: A Framework for Merging Symbolic and Neural Policy Learning

LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models

Exploring Neural Granger Causality with xLSTMs: Unveiling Temporal Dependencies in Complex Data

ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding

Object-Centric Concept-Bottlenecks

Where is the Truth? The Risk of Getting Confounded in a Continual World

When Causal Dynamics Matter: Adapting Causal Strategies through Meta-Aware Interventions

Core Tokensets for Data-efficient Sequential Training of Transformers

Hyperparameter Optimization via Interacting with Probabilistic Circuits

The Challenging Growth: Evaluating the Scalability of Causal Models

xLSTM-Mixer: Multivariate Time Series Forecasting by Mixing via Scalar Memories

Right on Time: Revising Time Series Models by Constraining their Explanations

Scaling Probabilistic Circuits via Data Partitioning

Bongard in Wonderland: Visual Puzzles that Still Make AI Go Mad?

Derivative Causal Models: Modeling Causality at Mixed Scales of Observation