Jonas Geiping

JonasGeiping's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper 23 days ago

Pitfalls in Evaluating Language Model Forecasters

Paper • 2506.00723 • Published 26 days ago • 3

authored 2 papers 5 months ago

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

Paper • 2502.05171 • Published Feb 7 • 142

Great Models Think Alike and this Undermines AI Oversight

Paper • 2502.04313 • Published Feb 6 • 34

authored a paper about 1 year ago

Transformers Can Do Arithmetic with the Right Embeddings

Paper • 2405.17399 • Published May 27, 2024 • 55

authored 9 papers over 1 year ago

Coercing LLMs to do and reveal (almost) anything

Paper • 2402.14020 • Published Feb 21, 2024 • 13

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

Paper • 2401.12070 • Published Jan 22, 2024 • 45

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

Paper • 2212.03860 • Published Dec 7, 2022 • 1

A Cookbook of Self-Supervised Learning

Paper • 2304.12210 • Published Apr 24, 2023 • 4

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

Paper • 2302.03668 • Published Feb 7, 2023 • 1

Multiframe Motion Coupling for Video Super Resolution

Paper • 1611.07767 • Published Nov 23, 2016

Stochastic Training is Not Necessary for Generalization

Paper • 2109.14119 • Published Sep 29, 2021

NEFTune: Noisy Embeddings Improve Instruction Finetuning

Paper • 2310.05914 • Published Oct 9, 2023 • 14

Object Recognition as Next Token Prediction

Paper • 2312.02142 • Published Dec 4, 2023 • 14

authored 3 papers almost 2 years ago

On the Exploitability of Instruction Tuning

Paper • 2306.17194 • Published Jun 28, 2023 • 9

Cramming: Training a Language Model on a Single GPU in One Day

Paper • 2212.14034 • Published Dec 28, 2022

A Watermark for Large Language Models

Paper • 2301.10226 • Published Jan 24, 2023 • 9

authored 4 papers about 2 years ago

Bring Your Own Data! Self-Supervised Evaluation for Large Language Models

Paper • 2306.13651 • Published Jun 23, 2023 • 15

On the Reliability of Watermarks for Large Language Models

Paper • 2306.04634 • Published Jun 7, 2023 • 5

Understanding and Mitigating Copying in Diffusion Models

Paper • 2305.20086 • Published May 31, 2023 • 3

Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robust

Paper • 2305.20030 • Published May 31, 2023 • 8