Kristian Kersting

18

Papers

11

Total Citations

Papers (18)

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

LEDITS++: Limitless Image Editing using Text-to-Image Models

Mechanistic Design and Scaling of Hybrid Architectures

Learning to Intervene on Concept Bottlenecks

Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting With Their Explanations

Interactive Disentanglement: Learning Concepts by Interacting With Their Prototype Representations

Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models

Rickrolling the Artist: Injecting Backdoors into Text Encoders for Text-to-Image Synthesis

Vision Relation Transformer for Unbiased Scene Graph Generation

ART: Adaptive Relation Tuning for Generalized Relation Prediction

Interventional Sum-Product Networks: Causal Inference with Tractable Probabilistic Models

SEGA: Instructing Text-to-Image Models using Semantic Guidance

Characteristic Circuits

Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstraction

MultiFusion: Fusing Pre-Trained Models for Multi-Lingual, Multi-Modal Image Generation

Do Not Marginalize Mechanisms, Rather Consolidate!

ATMAN: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation

Faster Attend-Infer-Repeat with Tractable Probabilistic Models