default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDJonas Geiping
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2025
[c53]Christina Runkel, Kanchana Vaishnavi Gandikota, Jonas Geiping, Carola-Bibiane Schönlieb, Michael Moeller:
Training Data Reconstruction: Privacy due to Uncertainty? CVPR Workshops 2025: 3502-3510- [c52]Niccolò Ajroldi, Antonio Orvieto, Jonas Geiping:
When, Where and Why to Average Weights? ICML 2025 - [c51]Valentyn Boreiko, Alexander Panfilov, Václav Vorácek, Matthias Hein, Jonas Geiping:
An Interpretable N-gram Perplexity Threat Model for Large Language Model Jailbreaks. ICML 2025 - [c50]Shashwat Goel, Joschka Strüber, Ilze Amanda Auzina, Karuna K. Chandra, Ponnurangam Kumaraguru, Douwe Kiela, Ameya Prabhu, Matthias Bethge, Jonas Geiping:
Great Models Think Alike and this Undermines AI Oversight. ICML 2025 - [c49]Jie S. Li, Jonas Geiping, Micah Goldblum, Aniruddha Saha, Tom Goldstein:
LLM-Generated Passphrases That Are Secure and Easy to Remember. NAACL (Findings) 2025: 5216-5234 - [i86]Guinan Su, Jonas Geiping:
Fine, I'll Merge It Myself: A Multi-Fidelity Framework for Automated Model Merging. CoRR abs/2502.04030 (2025) - [i85]Shashwat Goel, Joschka Strüber, Ilze Amanda Auzina, Karuna K. Chandra, Ponnurangam Kumaraguru, Douwe Kiela, Ameya Prabhu, Matthias Bethge, Jonas Geiping:
Great Models Think Alike and this Undermines AI Oversight. CoRR abs/2502.04313 (2025) - [i84]Jonas Geiping, Sean McLeish, Neel Jain, John Kirchenbauer, Siddharth Singh, Brian R. Bartoldson, Bhavya Kailkhura
, Abhinav Bhatele, Tom Goldstein:
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach. CoRR abs/2502.05171 (2025) - [i83]Niccolò Ajroldi, Antonio Orvieto, Jonas Geiping:
When, Where and Why to Average Weights? CoRR abs/2502.06761 (2025) - [i82]Siddharth Singh, Prajwal Singhania, Aditya K. Ranjan, John Kirchenbauer, Jonas Geiping, Yuxin Wen, Neel Jain, Abhimanyu Hans, Manli Shu, Aditya Tomar, Tom Goldstein, Abhinav Bhatele:
Democratizing AI: Open-source Scalable LLM Training on GPU-based Supercomputers. CoRR abs/2502.08145 (2025) - [i81]Shiven Sinha, Shashwat Goel, Ponnurangam Kumaraguru, Jonas Geiping, Matthias Bethge, Ameya Prabhu:
Can Language Models Falsify? Evaluating Algorithmic Reasoning with Counterexample Creation. CoRR abs/2502.19414 (2025) - [i80]Fay Elhassan, Niccolò Ajroldi, Antonio Orvieto, Jonas Geiping:
Can you Finetune your Binoculars? Embedding Text Watermarks into the Weights of Large Language Models. CoRR abs/2504.06446 (2025) - [i79]Alexander Panfilov, Paul Kassianik, Maksym Andriushchenko, Jonas Geiping:
Capability-Based Scaling Laws for LLM Red-Teaming. CoRR abs/2505.20162 (2025) - [i78]Daniel Paleka, Shashwat Goel, Jonas Geiping, Florian Tramèr:
Pitfalls in Evaluating Language Model Forecasters. CoRR abs/2506.00723 (2025) - [i77]Teodora Sreckovic, Jonas Geiping, Antonio Orvieto:
Is your batch size the problem? Revisiting the Adam-SGD gap in language modeling. CoRR abs/2506.12543 (2025) - [i76]Guinan Su, Li Shen, Lu Yin, Shiwei Liu, Yanwu Yang, Jonas Geiping:
GPTailor: Large Language Model Pruning Through Layer Cutting and Stitching. CoRR abs/2506.20480 (2025) - [i75]Nikhil Chandak, Shashwat Goel, Ameya Prabhu, Moritz Hardt, Jonas Geiping:
Answer Matching Outperforms Multiple Choice for Language Model Evaluation. CoRR abs/2507.02856 (2025) - [i74]Yanwu Yang, Guinan Su, Jiesi Hu, Francesco Sammarco, Jonas Geiping, Thomas Wolfers:
MedSAMix: A Training-Free Model Merging Approach for Medical Image Segmentation. CoRR abs/2508.11032 (2025) - [i73]Akshit Sinha, Arvindh Arun, Shashwat Goel, Steffen Staab, Jonas Geiping:
The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs. CoRR abs/2509.09677 (2025) - [i72]Alexander Panfilov, Evgenii Kortukov, Kristina Nikolic, Matthias Bethge, Sebastian Lapuschkin, Wojciech Samek, Ameya Prabhu, Maksym Andriushchenko, Jonas Geiping:
Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLMs. CoRR abs/2509.18058 (2025) - [i71]Xueyan Li, Guinan Su, Mrinmaya Sachan, Jonas Geiping:
Sample Smart, Not Hard: Correctness-First Decoding for Better Reasoning in LLMs. CoRR abs/2510.05987 (2025) - [i70]Albert Catalan-Tatjer, Niccolò Ajroldi, Jonas Geiping:
Training Dynamics Impact Post-Training Quantization Robustness. CoRR abs/2510.06213 (2025) - [i69]Mikhail Terekhov, Alexander Panfilov, Daniil Dzenhaliou, Caglar Gulcehre, Maksym Andriushchenko, Ameya Prabhu, Jonas Geiping:
Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols. CoRR abs/2510.09462 (2025) - [i68]Guinan Su, Yanwu Yang, Li Shen, Lu Yin, Shiwei Liu, Jonas Geiping:
Rewiring Experts on the Fly:Continuous Rerouting for Better Online Adaptation in Mixture-of-Expert models. CoRR abs/2510.14853 (2025) - [i67]Jonas Geiping, Xinyu Yang, Guinan Su:
Efficient Parallel Samplers for Recurrent-Depth Models and Their Connection to Diffusion Language Models. CoRR abs/2510.14961 (2025) - [i66]Keyu Wang, Tian Lyu, Guinan Su, Jonas Geiping, Lu Yin, Marco Canini, Shiwei Liu:
When Fewer Layers Break More Chains: Layer Pruning Harms Test-Time Scaling in LLMs. CoRR abs/2510.22228 (2025) - [i65]Sean McLeish, Ang Li, John Kirchenbauer, Dayal Singh Kalra, Brian R. Bartoldson, Bhavya Kailkhura, Avi Schwarzschild, Jonas Geiping, Tom Goldstein, Micah Goldblum:
Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence. CoRR abs/2511.07384 (2025) - [i64]Shashwat Goel, Rishi Hazra, Dulhan Jayalath, Timon Willi, Parag Jain, William F. Shen, Ilias Leontiadis, Francesco Barbieri, Yoram Bachrach, Jonas Geiping, Chenxi Whitehouse:
Training AI Co-Scientists Using Rubric Rewards. CoRR abs/2512.23707 (2025) - [i63]Nikhil Chandak, Shashwat Goel, Ameya Prabhu, Moritz Hardt, Jonas Geiping:
Scaling Open-Ended Reasoning to Predict the Future. CoRR abs/2512.25070 (2025) - 2024
- [c48]Kaiyu Yue, Bor-Chun Chen, Jonas Geiping, Hengduo Li, Tom Goldstein, Ser-Nam Lim:
Object Recognition as Next Token Prediction. CVPR 2024: 16645-16656 - [c47]Gowthami Somepalli, Anubhav Gupta, Kamal Gupta, Shramay Palta, Micah Goldblum, Jonas Geiping, Abhinav Shrivastava, Tom Goldstein:
Investigating Style Similarity in Diffusion Models. ECCV (66) 2024: 143-160 - [c46]Agniv Sharma, Jonas Geiping:
Efficiently Dispatching Flash Attention For Partially Filled Attention Masks. ENLSP 2024: 423-442 - [c45]Arpit Bansal, Hong-Min Chu, Avi Schwarzschild, Soumyadip Sengupta, Micah Goldblum, Jonas Geiping, Tom Goldstein:
Universal Guidance for Diffusion Models. ICLR 2024 - [c44]Neel Jain, Ping-yeh Chiang, Yuxin Wen, John Kirchenbauer, Hong-Min Chu, Gowthami Somepalli, Brian R. Bartoldson, Bhavya Kailkhura, Avi Schwarzschild, Aniruddha Saha, Micah Goldblum, Jonas Geiping, Tom Goldstein:
NEFTune: Noisy Embeddings Improve Instruction Finetuning. ICLR 2024 - [c43]John Kirchenbauer, Jonas Geiping, Yuxin Wen, Manli Shu, Khalid Saifullah, Kezhi Kong, Kasun Fernando, Aniruddha Saha, Micah Goldblum, Tom Goldstein:
On the Reliability of Watermarks for Large Language Models. ICLR 2024 - [c42]Abhimanyu Hans, Avi Schwarzschild, Valeriia Cherepanova, Hamid Kazemi, Aniruddha Saha, Micah Goldblum, Jonas Geiping, Tom Goldstein:
Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text. ICML 2024: 17519-17537 - [c41]Abhimanyu Hans, John Kirchenbauer, Yuxin Wen, Neel Jain, Hamid Kazemi, Prajwal Singhania, Siddharth Singh, Gowthami Somepalli, Jonas Geiping, Abhinav Bhatele, Tom Goldstein:
Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs. NeurIPS 2024 - [c40]Sean McLeish, Arpit Bansal, Alex Stein, Neel Jain, John Kirchenbauer, Brian R. Bartoldson, Bhavya Kailkhura, Abhinav Bhatele, Jonas Geiping, Avi Schwarzschild, Tom Goldstein:
Transformers Can Do Arithmetic with the Right Embeddings. NeurIPS 2024 - [c39]Gowthami Somepalli, Arkabandhu Chowdhury, Jonas Geiping, Ronen Basri, Tom Goldstein, David Jacobs:
CALVIN: Improved Contextual Video Captioning via Instruction Tuning. NeurIPS 2024 - [c38]Yuxin Wen, Leo Marchyok, Sanghyun Hong, Jonas Geiping, Tom Goldstein, Nicholas Carlini:
Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models. NeurIPS 2024 - [c37]Siddharth Singh, Prajwal Singhania, Aditya K. Ranjan, John Kirchenbauer, Jonas Geiping, Yuxin Wen, Neel Jain, Abhimanyu Hans, Manli Shu, Aditya Tomar, Tom Goldstein, Abhinav Bhatele:
Democratizing AI: Open-source Scalable LLM Training on GPU-based Supercomputers. SC 2024: 4 - [i62]Abhimanyu Hans, Avi Schwarzschild, Valeriia Cherepanova, Hamid Kazemi, Aniruddha Saha, Micah Goldblum, Jonas Geiping, Tom Goldstein:
Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text. CoRR abs/2401.12070 (2024) - [i61]Jonas Geiping, Alex Stein, Manli Shu, Khalid Saifullah, Yuxin Wen, Tom Goldstein:
Coercing LLMs to do and reveal (almost) anything. CoRR abs/2402.14020 (2024) - [i60]Hamid Kazemi, Atoosa Malemir Chegini, Jonas Geiping, Soheil Feizi, Tom Goldstein:
What do we learn from inverting CLIP models? CoRR abs/2403.02580 (2024) - [i59]Hossein Souri, Arpit Bansal, Hamid Kazemi, Liam Fowl, Aniruddha Saha, Jonas Geiping, Andrew Gordon Wilson, Rama Chellappa, Tom Goldstein, Micah Goldblum:
Generating Potent Poisons and Backdoors from Scratch with Guided Diffusion. CoRR abs/2403.16365 (2024) - [i58]Yuxin Wen, Leo Marchyok, Sanghyun Hong, Jonas Geiping, Tom Goldstein, Nicholas Carlini:
Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models. CoRR abs/2404.01231 (2024) - [i57]Gowthami Somepalli, Anubhav Gupta, Kamal Gupta, Shramay Palta, Micah Goldblum, Jonas Geiping, Abhinav Shrivastava, Tom Goldstein:
Measuring Style Similarity in Diffusion Models. CoRR abs/2404.01292 (2024) - [i56]John Kirchenbauer, Garrett Honke, Gowthami Somepalli, Jonas Geiping, Daphne Ippolito, Katherine Lee, Tom Goldstein, David Andre:
LMD3: Language Model Data Density Dependence. CoRR abs/2405.06331 (2024) - [i55]Sean McLeish, Arpit Bansal, Alex Stein, Neel Jain, John Kirchenbauer, Brian R. Bartoldson, Bhavya Kailkhura, Abhinav Bhatele, Jonas Geiping, Avi Schwarzschild, Tom Goldstein:
Transformers Can Do Arithmetic with the Right Embeddings. CoRR abs/2405.17399 (2024) - [i54]Xiangyu Qi, Yangsibo Huang, Yi Zeng, Edoardo Debenedetti, Jonas Geiping, Luxi He, Kaixuan Huang, Udari Madhushani, Vikash Sehwag, Weijia Shi, Boyi Wei, Tinghao Xie, Danqi Chen, Pin-Yu Chen, Jeffrey Ding, Ruoxi Jia, Jiaqi Ma, Arvind Narayanan, Weijie J. Su, Mengdi Wang, Chaowei Xiao, Bo Li, Dawn Song, Peter Henderson, Prateek Mittal:
AI Risk Management Should Incorporate Both Safety and Security. CoRR abs/2405.19524 (2024) - [i53]Abhimanyu Hans, Yuxin Wen, Neel Jain, John Kirchenbauer, Hamid Kazemi, Prajwal Singhania, Siddharth Singh, Gowthami Somepalli, Jonas Geiping, Abhinav Bhatele, Tom Goldstein:
Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs. CoRR abs/2406.10209 (2024) - [i52]Agniv Sharma, Jonas Geiping:
Efficiently Dispatching Flash Attention For Partially Filled Attention Masks. CoRR abs/2409.15097 (2024) - [i51]Valentyn Boreiko, Alexander Panfilov, Václav Vorácek, Matthias Hein, Jonas Geiping:
A Realistic Threat Model for Large Language Model Jailbreaks. CoRR abs/2410.16222 (2024) - [i50]Christina Runkel, Kanchana Vaishnavi Gandikota, Jonas Geiping, Carola-Bibiane Schönlieb, Michael Moeller:
Training Data Reconstruction: Privacy due to Uncertainty? CoRR abs/2412.08544 (2024) - 2023
- [j2]Soumya Suvra Ghosal, Souradip Chakraborty, Jonas Geiping, Furong Huang, Dinesh Manocha, Amrit S. Bedi:
A Survey on the Possibilities & Impossibilities of AI-generated Text Detection. Trans. Mach. Learn. Res. 2023 (2023) - [c36]Arpit Bansal, Hong-Min Chu, Avi Schwarzschild, Soumyadip Sengupta, Micah Goldblum, Jonas Geiping, Tom Goldstein:
Universal Guidance for Diffusion Models. CVPR Workshops 2023: 843-852 - [c35]Gowthami Somepalli, Vasu Singla, Micah Goldblum, Jonas Geiping, Tom Goldstein:
Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models. CVPR 2023: 6048-6058 - [c34]Yuxin Wen, Jonas Geiping, Micah Goldblum, Tom Goldstein:
STYX: Adaptive Poisoning Attacks Against Byzantine-Robust Defenses in Federated Learning. ICASSP 2023: 1-5 - [c33]Ping-yeh Chiang, Renkun Ni, David Yu Miller, Arpit Bansal, Jonas Geiping, Micah Goldblum, Tom Goldstein:
Loss Landscapes are All You Need: Neural Network Generalization Can Be Explained Without the Implicit Bias of Gradient Descent. ICLR 2023 - [c32]Hong-Min Chu, Jonas Geiping, Liam H. Fowl, Micah Goldblum, Tom Goldstein:
Panning for Gold in Federated Learning: Targeted Text Extraction under Arbitrarily Large-Scale Aggregation. ICLR 2023 - [c31]Liam H. Fowl, Jonas Geiping, Steven Reich, Yuxin Wen, Wojciech Czaja, Micah Goldblum, Tom Goldstein:
Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models. ICLR 2023 - [c30]Jonas Geiping, Micah Goldblum, Gowthami Somepalli, Ravid Shwartz-Ziv, Tom Goldstein, Andrew Gordon Wilson:
How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization. ICLR 2023 - [c29]Khalid Saifullah, Yuxin Wen, Jonas Geiping, Micah Goldblum, Tom Goldstein:
Seeing in Words: Learning to Classify through Language Bottlenecks. Tiny Papers @ ICLR 2023 - [c28]Yuxin Wen, Arpit Bansal, Hamid Kazemi, Eitan Borgnia, Micah Goldblum, Jonas Geiping, Tom Goldstein:
Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries. ICLR 2023 - [c27]Jonas Geiping, Tom Goldstein:
Cramming: Training a Language Model on a single GPU in one day. ICML 2023: 11117-11143 - [c26]John Kirchenbauer, Jonas Geiping, Yuxin Wen, Jonathan Katz, Ian Miers, Tom Goldstein:
A Watermark for Large Language Models. ICML 2023: 17061-17084 - [c25]Arpit Bansal, Eitan Borgnia, Hong-Min Chu, Jie Li, Hamid Kazemi, Furong Huang, Micah Goldblum, Jonas Geiping, Tom Goldstein:
Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise. NeurIPS 2023 - [c24]Valeriia Cherepanova, Roman Levin, Gowthami Somepalli, Jonas Geiping, C. Bayan Bruss, Andrew Gordon Wilson, Tom Goldstein, Micah Goldblum:
A Performance-Driven Benchmark for Feature Selection in Tabular Deep Learning. NeurIPS 2023 - [c23]Pedro Sandoval Segura, Vasu Singla, Jonas Geiping, Micah Goldblum, Tom Goldstein:
What Can We Learn from Unlearnable Datasets? NeurIPS 2023 - [c22]Manli Shu, Jiongxiao Wang, Chen Zhu, Jonas Geiping, Chaowei Xiao, Tom Goldstein:
On the Exploitability of Instruction Tuning. NeurIPS 2023 - [c21]Gowthami Somepalli, Vasu Singla, Micah Goldblum, Jonas Geiping, Tom Goldstein:
Understanding and Mitigating Copying in Diffusion Models. NeurIPS 2023 - [c20]Yuxin Wen, Neel Jain, John Kirchenbauer, Micah Goldblum, Jonas Geiping, Tom Goldstein:
Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery. NeurIPS 2023 - [c19]Yuxin Wen, John Kirchenbauer, Jonas Geiping, Tom Goldstein:
Tree-Rings Watermarks: Invisible Fingerprints for Diffusion Images. NeurIPS 2023 - [c18]Jie S. Li, Yow-Ting Shiue, Yong-Siang Shih, Jonas Geiping:
Augmenters at SemEval-2023 Task 1: Enhancing CLIP in Handling Compositionality and Ambiguity for Zero-Shot Visual WSD through Prompt Augmentation and Text-To-Image Diffusion. SemEval@ACL 2023: 44-49 - [i49]John Kirchenbauer, Jonas Geiping, Yuxin Wen, Jonathan Katz, Ian Miers, Tom Goldstein:
A Watermark for Large Language Models. CoRR abs/2301.10226 (2023) - [i48]Yuxin Wen, Neel Jain, John Kirchenbauer, Micah Goldblum, Jonas Geiping, Tom Goldstein:
Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery. CoRR abs/2302.03668 (2023) - [i47]Arpit Bansal, Hong-Min Chu, Avi Schwarzschild, Soumyadip Sengupta, Micah Goldblum, Jonas Geiping, Tom Goldstein:
Universal Guidance for Diffusion Models. CoRR abs/2302.07121 (2023) - [i46]Pedro Sandoval Segura, Jonas Geiping, Tom Goldstein:
JPEG Compressed Images Can Bypass Protections Against AI Editing. CoRR abs/2304.02234 (2023) - [i45]Randall Balestriero, Mark Ibrahim, Vlad Sobal, Ari Morcos, Shashank Shekhar, Tom Goldstein, Florian Bordes, Adrien Bardes, Grégoire Mialon, Yuandong Tian, Avi Schwarzschild, Andrew Gordon Wilson, Jonas Geiping, Quentin Garrido, Pierre Fernandez, Amir Bar, Hamed Pirsiavash, Yann LeCun, Micah Goldblum:
A Cookbook of Self-Supervised Learning. CoRR abs/2304.12210 (2023) - [i44]Pedro Sandoval Segura, Vasu Singla, Jonas Geiping, Micah Goldblum, Tom Goldstein:
What Can We Learn from Unlearnable Datasets? CoRR abs/2305.19254 (2023) - [i43]Yuxin Wen, John Kirchenbauer, Jonas Geiping, Tom Goldstein:
Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robust. CoRR abs/2305.20030 (2023) - [i42]Gowthami Somepalli, Vasu Singla, Micah Goldblum, Jonas Geiping, Tom Goldstein:
Understanding and Mitigating Copying in Diffusion Models. CoRR abs/2305.20086 (2023) - [i41]John Kirchenbauer, Jonas Geiping, Yuxin Wen, Manli Shu, Khalid Saifullah, Kezhi Kong, Kasun Fernando, Aniruddha Saha, Micah Goldblum, Tom Goldstein:
On the Reliability of Watermarks for Large Language Models. CoRR abs/2306.04634 (2023) - [i40]Neel Jain, Khalid Saifullah, Yuxin Wen, John Kirchenbauer, Manli Shu, Aniruddha Saha, Micah Goldblum, Jonas Geiping, Tom Goldstein:
Bring Your Own Data! Self-Supervised Evaluation for Large Language Models. CoRR abs/2306.13651 (2023) - [i39]Manli Shu, Jiongxiao Wang, Chen Zhu, Jonas Geiping, Chaowei Xiao, Tom Goldstein:
On the Exploitability of Instruction Tuning. CoRR abs/2306.17194 (2023) - [i38]Khalid Saifullah, Yuxin Wen, Jonas Geiping, Micah Goldblum, Tom Goldstein:
Seeing in Words: Learning to Classify through Language Bottlenecks. CoRR abs/2307.00028 (2023) - [i37]Jie S. Li, Yow-Ting Shiue, Yong-Siang Shih, Jonas Geiping:
Augmenters at SemEval-2023 Task 1: Enhancing CLIP in Handling Compositionality and Ambiguity for Zero-Shot Visual WSD through Prompt Augmentation and Text-To-Image Diffusion. CoRR abs/2307.05564 (2023) - [i36]Neel Jain, Avi Schwarzschild, Yuxin Wen, Gowthami Somepalli, John Kirchenbauer, Ping-yeh Chiang, Micah Goldblum, Aniruddha Saha, Jonas Geiping, Tom Goldstein:
Baseline Defenses for Adversarial Attacks Against Aligned Language Models. CoRR abs/2309.00614 (2023) - [i35]Neel Jain, Ping-yeh Chiang, Yuxin Wen, John Kirchenbauer, Hong-Min Chu, Gowthami Somepalli, Brian R. Bartoldson, Bhavya Kailkhura, Avi Schwarzschild, Aniruddha Saha, Micah Goldblum, Jonas Geiping, Tom Goldstein:
NEFTune: Noisy Embeddings Improve Instruction Finetuning. CoRR abs/2310.05914 (2023) - [i34]Soumya Suvra Ghosal, Souradip Chakraborty, Jonas Geiping, Furong Huang, Dinesh Manocha, Amrit Singh Bedi:
Towards Possibilities & Impossibilities of AI-generated Text Detection: A Survey. CoRR abs/2310.15264 (2023) - [i33]Vasu Singla, Pedro Sandoval Segura, Micah Goldblum, Jonas Geiping, Tom Goldstein:
A Simple and Efficient Baseline for Data Attribution on Images. CoRR abs/2311.03386 (2023) - [i32]Valeriia Cherepanova, Roman Levin, Gowthami Somepalli, Jonas Geiping, C. Bayan Bruss, Andrew Gordon Wilson, Tom Goldstein, Micah Goldblum:
A Performance-Driven Benchmark for Feature Selection in Tabular Deep Learning. CoRR abs/2311.05877 (2023) - [i31]Kaiyu Yue, Bor-Chun Chen, Jonas Geiping, Hengduo Li, Tom Goldstein, Ser-Nam Lim:
Object Recognition as Next Token Prediction. CoRR abs/2312.02142 (2023) - 2022
- [c17]Kanchana Vaishnavi Gandikota, Jonas Geiping, Zorah Lähner, Adam Czaplinski, Michael Möller:
A Simple Strategy to Provable Invariance via Orbit Mapping. ACCV (5) 2022: 387-405 - [c16]Pedro Sandoval Segura, Vasu Singla, Liam Fowl, Jonas Geiping, Micah Goldblum, David Jacobs, Tom Goldstein:
Poisons that are learned faster are more effective. CVPR Workshops 2022: 197-204 - [c15]Liam H. Fowl, Jonas Geiping, Wojciech Czaja, Micah Goldblum, Tom Goldstein:
Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Models. ICLR 2022 - [c14]Jonas Geiping, Micah Goldblum, Phillip Pope, Michael Moeller, Tom Goldstein:
Stochastic Training is Not Necessary for Generalization. ICLR 2022 - [c13]Yuxin Wen, Jonas Geiping, Liam Fowl, Micah Goldblum, Tom Goldstein:
Fishing for User Data in Large-Batch Federated Learning via Gradient Magnification. ICML 2022: 23668-23684 - [c12]Pedro Sandoval Segura, Vasu Singla, Jonas Geiping, Micah Goldblum, Tom Goldstein, David Jacobs:
Autoregressive Perturbations for Data Poisoning. NeurIPS 2022 - [i30]Liam Fowl, Jonas Geiping, Steven Reich, Yuxin Wen, Wojtek Czaja, Micah Goldblum, Tom Goldstein:
Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models. CoRR abs/2201.12675 (2022) - [i29]Yuxin Wen, Jonas Geiping, Liam Fowl, Micah Goldblum, Tom Goldstein:
Fishing for User Data in Large-Batch Federated Learning via Gradient Magnification. CoRR abs/2202.00580 (2022) - [i28]Pedro Sandoval Segura, Vasu Singla, Liam Fowl, Jonas Geiping, Micah Goldblum, David Jacobs, Tom Goldstein:
Poisons that are learned faster are more effective. CoRR abs/2204.08615 (2022) - [i27]Pedro Sandoval Segura, Vasu Singla, Jonas Geiping, Micah Goldblum, Tom Goldstein, David W. Jacobs:
Autoregressive Perturbations for Data Poisoning. CoRR abs/2206.03693 (2022) - [i26]Arpit Bansal, Eitan Borgnia, Hong-Min Chu, Jie S. Li, Hamid Kazemi, Furong Huang, Micah Goldblum, Jonas Geiping, Tom Goldstein:
Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise. CoRR abs/2208.09392 (2022) - [i25]Kanchana Vaishnavi Gandikota, Jonas Geiping, Zorah Lähner, Adam Czaplinski, Michael Möller:
A Simple Strategy to Provable Invariance via Orbit Mapping. CoRR abs/2209.11916 (2022) - [i24]Jonas Geiping, Micah Goldblum, Gowthami Somepalli, Ravid Shwartz-Ziv, Tom Goldstein, Andrew Gordon Wilson:
How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization. CoRR abs/2210.06441 (2022) - [i23]Yuxin Wen, Jonas Geiping, Liam Fowl, Hossein Souri, Rama Chellappa, Micah Goldblum, Tom Goldstein:
Thinking Two Moves Ahead: Anticipating Other Users Improves Backdoor Attacks in Federated Learning. CoRR abs/2210.09305 (2022) - [i22]Yuxin Wen, Arpit Bansal, Hamid Kazemi, Eitan Borgnia, Micah Goldblum, Jonas Geiping, Tom Goldstein:
Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries. CoRR abs/2210.10750 (2022) - [i21]Renkun Ni, Ping-yeh Chiang, Jonas Geiping, Micah Goldblum, Andrew Gordon Wilson, Tom Goldstein:
K-SAM: Sharpness-Aware Minimization at the Speed of SGD. CoRR abs/2210.12864 (2022) - [i20]Gowthami Somepalli, Vasu Singla, Micah Goldblum, Jonas Geiping, Tom Goldstein:
Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models. CoRR abs/2212.03860 (2022) - [i19]Jonas Geiping, Tom Goldstein:
Cramming: Training a Language Model on a Single GPU in One Day. CoRR abs/2212.14034 (2022) - 2021
- [b1]Jonas Geiping:
Modern optimization techniques in computer vision: from variational models to machine learning security. University of Siegen, Germany, 2021 - [c11]Eitan Borgnia, Valeriia Cherepanova, Liam Fowl, Amin Ghiasi, Jonas Geiping, Micah Goldblum, Tom Goldstein, Arjun Gupta:
Strong Data Augmentation Sanitizes Poisoning and Backdoor Attacks Without an Accuracy Tradeoff. ICASSP 2021: 3855-3859 - [c10]Jonas Geiping, Liam H. Fowl, W. Ronny Huang, Wojciech Czaja, Gavin Taylor, Michael Moeller, Tom Goldstein:
Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching. ICLR 2021 - [c9]Liam Fowl, Micah Goldblum, Ping-yeh Chiang, Jonas Geiping, Wojciech Czaja, Tom Goldstein:
Adversarial Examples Make Strong Poisons. NeurIPS 2021: 30339-30351 - [i18]Jonas Geiping, Liam Fowl, Gowthami Somepalli, Micah Goldblum, Michael Moeller, Tom Goldstein:
What Doesn't Kill You Makes You Robust(er): Adversarial Training against Poisons and Backdoors. CoRR abs/2102.13624 (2021) - [i17]Eitan Borgnia, Jonas Geiping, Valeriia Cherepanova, Liam Fowl, Arjun Gupta, Amin Ghiasi, Furong Huang, Micah Goldblum, Tom Goldstein:
DP-InstaHide: Provably Defusing Poisoning and Backdoor Attacks with Differentially Private Data Augmentations. CoRR abs/2103.02079 (2021) - [i16]Liam Fowl, Ping-yeh Chiang, Micah Goldblum, Jonas Geiping, Arpit Bansal, Wojtek Czaja, Tom Goldstein:
Preventing Unauthorized Use of Proprietary Data: Poisoning for Secure Dataset Release. CoRR abs/2103.02683 (2021) - [i15]Kanchana Vaishnavi Gandikota, Jonas Geiping, Zorah Lähner, Adam Czaplinski, Michael Möller:
Training or Architecture? How to Incorporate Invariance in Neural Networks. CoRR abs/2106.10044 (2021) - [i14]Liam Fowl, Micah Goldblum, Ping-yeh Chiang, Jonas Geiping, Wojtek Czaja, Tom Goldstein:
Adversarial Examples Make Strong Poisons. CoRR abs/2106.10807 (2021) - [i13]Jonas Geiping, Jovita Lukasik, Margret Keuper, Michael Moeller:
DARTS for Inverse Problems: a Study on Hyperparameter Sensitivity. CoRR abs/2108.05647 (2021) - [i12]Jonas Geiping, Micah Goldblum, Phillip E. Pope, Michael Moeller, Tom Goldstein:
Stochastic Training is Not Necessary for Generalization. CoRR abs/2109.14119 (2021) - [i11]Liam Fowl, Jonas Geiping, Wojtek Czaja, Micah Goldblum, Tom Goldstein:
Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Models. CoRR abs/2110.13057 (2021) - 2020
- [c8]Jonas Geiping, Fjedor Gaede, Hartmut Bauermeister, Michael Moeller:
Fast Convex Relaxations using Graph Discretizations. BMVC 2020 - [c7]Ping-Yeh Chiang, Jonas Geiping, Micah Goldblum, Tom Goldstein, Renkun Ni, Steven Reich, Ali Shafahi:
Witchcraft: Efficient PGD Attacks with Random Step Size. ICASSP 2020: 3747-3751 - [c6]Micah Goldblum, Jonas Geiping, Avi Schwarzschild, Michael Moeller, Tom Goldstein:
Truth or backpropaganda? An empirical investigation of deep learning theory. ICLR 2020 - [c5]Jonas Geiping, Hartmut Bauermeister, Hannah Dröge, Michael Moeller:
Inverting Gradients - How easy is it to break privacy in federated learning? NeurIPS 2020 - [c4]W. Ronny Huang, Jonas Geiping, Liam Fowl, Gavin Taylor, Tom Goldstein:
MetaPoison: Practical General-purpose Clean-label Data Poisoning. NeurIPS 2020 - [i10]Jonas Geiping, Hartmut Bauermeister, Hannah Dröge, Michael Moeller:
Inverting Gradients - How easy is it to break privacy in federated learning? CoRR abs/2003.14053 (2020) - [i9]W. Ronny Huang, Jonas Geiping, Liam Fowl, Gavin Taylor, Tom Goldstein:
MetaPoison: Practical General-purpose Clean-label Data Poisoning. CoRR abs/2004.00225 (2020) - [i8]Jonas Geiping, Fjedor Gaede, Hartmut Bauermeister, Michael Moeller:
Fast Convex Relaxations using Graph Discretizations. CoRR abs/2004.11075 (2020) - [i7]Jonas Geiping, Liam Fowl, W. Ronny Huang, Wojciech Czaja, Gavin Taylor, Michael Moeller, Tom Goldstein:
Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching. CoRR abs/2009.02276 (2020) - [i6]Eitan Borgnia, Valeriia Cherepanova, Liam Fowl, Amin Ghiasi, Jonas Geiping, Micah Goldblum, Tom Goldstein, Arjun Gupta:
Strong Data Augmentation Sanitizes Poisoning and Backdoor Attacks Without an Accuracy Tradeoff. CoRR abs/2011.09527 (2020)
2010 – 2019
- 2019
- [c3]Jonas Geiping, Michael Moeller:
Parametric Majorization for Data-Driven Energy Minimization Methods. ICCV 2019: 10261-10272 - [c2]Andreas Görlitz, Jonas Geiping, Andreas Kolb:
Piecewise Rigid Scene Flow with Implicit Motion Segmentation. IROS 2019: 1758-1765 - [i5]Jonas Geiping, Michael Moeller:
Parametric Majorization for Data-Driven Energy Minimization Methods. CoRR abs/1908.06209 (2019) - [i4]Micah Goldblum, Jonas Geiping, Avi Schwarzschild, Michael Moeller, Tom Goldstein:
Truth or Backpropaganda? An Empirical Investigation of Deep Learning Theory. CoRR abs/1910.00359 (2019) - [i3]Ping-Yeh Chiang, Jonas Geiping, Micah Goldblum, Tom Goldstein, Renkun Ni, Steven Reich, Ali Shafahi:
WITCHcraft: Efficient PGD attacks with random step size. CoRR abs/1911.07989 (2019) - 2018
- [j1]Jonas Geiping, Michael Möller:
Composite Optimization by Nonconvex Majorization-Minimization. SIAM J. Imaging Sci. 11(4): 2494-2528 (2018) - [i2]Jonas Geiping, Michael Möller:
Composite Optimization by Nonconvex Majorization-Minimization. CoRR abs/1802.07072 (2018) - 2017
- [c1]Jonas Geiping, Hendrik Dirks, Daniel Cremers, Michael Möller:
Multiframe Motion Coupling for Video Super Resolution. EMMCVPR 2017: 123-138 - 2016
- [i1]Hendrik Dirks, Jonas Geiping, Daniel Cremers, Michael Möller:
Multiframe Motion Coupling via Infimal Convolution Regularization for Video Super Resolution. CoRR abs/1611.07767 (2016)
Coauthor Index
Liam Fowl
aka: Liam H. Fowl
aka: Liam H. Fowl
[c49] [i65] [c47] [c45] [c44] [c43] [c42] [i62] [i59] [i57] [c36] [c35] [c34] [c33] [c32] [c31] [c30] [c29] [c28] [c25] [c24] [c23] [c21] [c20] [i48] [i47] [i45] [i44] [i42] [i41] [i40] [i38] [i36] [i35] [i33] [i32] [c16] [c15] [c14] [c13] [c12] [i30] [i29] [i28] [i27] [i26] [i24] [i23] [i22] [i21] [i20] [c11] [c9] [i18] [i17] [i16] [i14] [i12] [i11] [c7] [c6] [i6] [i4] [i3]
[c49] [i84] [i82] [i65] [c48] [c47] [c45] [c44] [c43] [c42] [c41] [c40] [c39] [c38] [c37] [i62] [i61] [i60] [i59] [i58] [i57] [i56] [i55] [i53] [c36] [c35] [c34] [c33] [c32] [c31] [c30] [c29] [c28] [c27] [c26] [c25] [c24] [c23] [c22] [c21] [c20] [c19] [i49] [i48] [i47] [i46] [i45] [i44] [i43] [i42] [i41] [i40] [i39] [i38] [i36] [i35] [i33] [i32] [i31] [c16] [c15] [c14] [c13] [c12] [i30] [i29] [i28] [i27] [i26] [i24] [i23] [i22] [i21] [i20] [i19] [c11] [c10] [c9] [i18] [i17] [i16] [i14] [i12] [i11] [c7] [c6] [c4] [i9] [i7] [i6] [i4] [i3]
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2026-02-10 22:51 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
