Kristian Kersting

papers

1,109

total citations

papers (19)

Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models

CVPR 2023arXiv

471

citations

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

CVPR 2024arXiv

131

citations

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

CVPR 2021arXiv

128

citations

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

ICCV 2023arXiv

citations

Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstraction

NEURIPS 2023arXiv

citations

Mechanistic Design and Scaling of Hybrid Architectures

ICML 2024arXiv

citations

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

NEURIPS 2021arXiv

citations

ATMAN: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation

NEURIPS 2023arXiv

citations

Interactive Disentanglement: Learning Concepts by Interacting With Their Prototype Representations

CVPR 2022arXiv

citations

Learning to Intervene on Concept Bottlenecks

ICML 2024arXiv

citations

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

NEURIPS 2023arXiv

citations

Kristian Kersting

papers (19)

Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models

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

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

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

Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstraction

Mechanistic Design and Scaling of Hybrid Architectures

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

ATMAN: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation

Interactive Disentanglement: Learning Concepts by Interacting With Their Prototype Representations

Learning to Intervene on Concept Bottlenecks

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

Vision Relation Transformer for Unbiased Scene Graph Generation

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

Characteristic Circuits

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

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

Do Not Marginalize Mechanisms, Rather Consolidate!

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

ART: Adaptive Relation Tuning for Generalized Relation Prediction

papers (19)

Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models

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

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

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

Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstraction

Mechanistic Design and Scaling of Hybrid Architectures

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

ATMAN: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation

Interactive Disentanglement: Learning Concepts by Interacting With Their Prototype Representations

Learning to Intervene on Concept Bottlenecks

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

Vision Relation Transformer for Unbiased Scene Graph Generation

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

Characteristic Circuits

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

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

Do Not Marginalize Mechanisms, Rather Consolidate!

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

ART: Adaptive Relation Tuning for Generalized Relation Prediction