Jonas Geiping

18

Papers

690

Total Citations

1

Affiliations

Affiliations

University of Maryland, College Park

Papers (18)

Universal Guidance for Diffusion Models

On the Reliability of Watermarks for Large Language Models

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach

Object Recognition as Next Token Prediction

Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models

Parametric Majorization for Data-Driven Energy Minimization Methods

Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text

Understanding and Mitigating Copying in Diffusion Models

Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery

Tree-Rings Watermarks: Invisible Fingerprints for Diffusion Images

On the Exploitability of Instruction Tuning

What Can We Learn from Unlearnable Datasets?

MetaPoison: Practical General-purpose Clean-label Data Poisoning

Inverting Gradients - How easy is it to break privacy in federated learning?

Adversarial Examples Make Strong Poisons

Autoregressive Perturbations for Data Poisoning

Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise

A Performance-Driven Benchmark for Feature Selection in Tabular Deep Learning