On the Stability of Iterative Retraining of Generative Models on their own Data

30 September 2023

Papers citing "On the Stability of Iterative Retraining of Generative Models on their own Data"

35 / 35 papers shown

Title
Self-Consuming Generative Models with Adversarially Curated Data Xiukun Wei Xueru Zhang WIGM 39 0 0 14 May 2025
Information Retrieval in the Age of Generative AI: The RGB Model M. Garetto Alessandro Cornacchia Franco Galante Emilio Leonardi A. Nordio A. Tarable 134 0 0 29 Apr 2025
Recursive Training Loops in LLMs: How training data properties modulate distribution shift in generated data? Grgur Kovač Jérémy Perez Rémy Portelas Peter Ford Dominey Pierre-Yves Oudeyer 35 0 0 04 Apr 2025
Enhancing Domain-Specific Encoder Models with LLM-Generated Data: How to Leverage Ontologies, and How to Do Without Them Marc Felix Brinner Tarek Al Mustafa Sina Zarrieß 34 0 0 27 Mar 2025
Position: Model Collapse Does Not Mean What You Think Rylan Schaeffer Joshua Kazdan Alvan Caleb Arulandu Sanmi Koyejo 69 0 0 05 Mar 2025
A Theoretical Perspective: How to Prevent Model Collapse in Self-consuming Training Loops Shi Fu Yingjie Wang Yuzhu Chen Xinmei Tian Dacheng Tao 53 1 0 26 Feb 2025
Machine-generated text detection prevents language model collapse George Drayson Emine Yilmaz Vasileios Lampos DeLMO 62 0 0 21 Feb 2025
Escaping Collapse: The Strength of Weak Data for Large Language Model Training Kareem Amin Sara Babakniya Alex Bie Weiwei Kong Umar Syed Sergei Vassilvitskii 70 1 0 13 Feb 2025
Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges Nayoung Lee Ziyang Cai Avi Schwarzschild Kangwook Lee Dimitris Papailiopoulos ReLM VLM LRM AI4CE 83 4 0 03 Feb 2025
Rate of Model Collapse in Recursive Training A. Suresh A. Thangaraj Aditya Nanda Kishore Khandavally SyDa 27 5 0 23 Dec 2024
Universality of the $π^2/6$ Pathway in Avoiding Model Collapse Apratim Dey D. Donoho 58 5 0 30 Oct 2024
Collapse or Thrive? Perils and Promises of Synthetic Data in a Self-Generating World Joshua Kazdan Rylan Schaeffer Apratim Dey Matthias Gerstgrasser Rafael Rafailov D. Donoho Sanmi Koyejo 53 11 0 22 Oct 2024
Strong Model Collapse Elvis Dohmatob Yunzhen Feng Arjun Subramonian Julia Kempe 28 9 0 07 Oct 2024
Self-Improving Diffusion Models with Synthetic Data Sina Alemohammad Ahmed Imtiaz Humayun S. Agarwal John Collomosse Richard G. Baraniuk 30 11 0 29 Aug 2024
LLM See, LLM Do: Guiding Data Generation to Target Non-Differentiable Objectives Luísa Shimabucoro Sebastian Ruder Julia Kreutzer Marzieh Fadaee Sara Hooker SyDa 36 4 0 01 Jul 2024
A survey on the impact of AI-based recommenders on human behaviours: methodologies, outcomes and future directions Luca Pappalardo Emanuele Ferragina Salvatore Citraro Giuliano Cornacchia M. Nanni ... D. Gambetta Giovanni Mauro Virginia Morini Valentina Pansanella D. Pedreschi 46 9 0 29 Jun 2024
How Stable is Stable Diffusion under Recursive InPainting (RIP)? Javier Conde Miguel González Gonzalo Martínez Fernando Moral Elena Merino-Gómez Pedro Reviriego DiffM 42 3 0 27 Jun 2024
Understanding Hallucinations in Diffusion Models through Mode Interpolation Sumukh K. Aithal Pratyush Maini Zachary Chase Lipton J. Zico Kolter DiffM 40 19 0 13 Jun 2024
Beyond Model Collapse: Scaling Up with Synthesized Data Requires Reinforcement Yunzhen Feng Elvis Dohmatob Pu Yang Francois Charton Julia Kempe 53 17 0 11 Jun 2024
Automating Data Annotation under Strategic Human Agents: Risks and Potential Solutions Tian Xie Xueru Zhang 35 3 0 12 May 2024
Heat Death of Generative Models in Closed-Loop Learning Matteo Marchi Stefano Soatto Pratik Chaudhari Paulo Tabuada SyDa VLM AI4CE 33 14 0 02 Apr 2024
Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Data Matthias Gerstgrasser Rylan Schaeffer Apratim Dey Rafael Rafailov Henry Sleight ... Andrey Gromov Daniel A. Roberts Diyi Yang D. Donoho Oluwasanmi Koyejo 26 52 0 01 Apr 2024
Human vs. Generative AI in Content Creation Competition: Symbiosis or Conflict? Fan Yao Chuanhao Li Denis Nekipelov Hongning Wang Haifeng Xu 43 14 0 23 Feb 2024
Towards Theoretical Understandings of Self-Consuming Generative Models Shi Fu Sen Zhang Yingjie Wang Xinmei Tian Dacheng Tao 36 9 0 19 Feb 2024
Model Collapse Demystified: The Case of Regression Elvis Dohmatob Yunzhen Feng Julia Kempe 39 32 0 12 Feb 2024
Beware of Words: Evaluating the Lexical Richness of Conversational Large Language Models Gonzalo Martínez José Alberto Hernández Javier Conde Pedro Reviriego Elena Merino-Gómez 16 7 0 11 Feb 2024
Self-Correcting Self-Consuming Loops for Generative Model Training Nate Gillman Michael Freeman Daksh Aggarwal Chia-Hong Hsu Calvin Luo Yonglong Tian Chen Sun 33 13 0 11 Feb 2024
A Tale of Tails: Model Collapse as a Change of Scaling Laws Elvis Dohmatob Yunzhen Feng Pu Yang Francois Charton Julia Kempe 29 64 0 10 Feb 2024
Iterated Denoising Energy Matching for Sampling from Boltzmann Densities Tara Akhound-Sadegh Jarrid Rector-Brooks A. Bose Sarthak Mittal Pablo Lemos ... Siamak Ravanbakhsh Gauthier Gidel Yoshua Bengio Nikolay Malkin Alexander Tong DiffM 40 41 0 09 Feb 2024
Large Language Models Suffer From Their Own Output: An Analysis of the Self-Consuming Training Loop Martin Briesch Dominik Sobania Franz Rothlauf 35 55 0 28 Nov 2023
Sparks of Artificial General Intelligence: Early experiments with GPT-4 Sébastien Bubeck Varun Chandrasekaran Ronen Eldan J. Gehrke Eric Horvitz ... Scott M. Lundberg Harsha Nori Hamid Palangi Marco Tulio Ribeiro Yi Zhang ELM AI4MH AI4CE ALM 298 2,232 0 22 Mar 2023
Diffusion Models are Minimax Optimal Distribution Estimators Kazusato Oko Shunta Akiyama Taiji Suzuki DiffM 72 85 0 03 Mar 2023
Zero-Shot Text-to-Image Generation Aditya A. Ramesh Mikhail Pavlov Gabriel Goh Scott Gray Chelsea Voss Alec Radford Mark Chen Ilya Sutskever VLM 255 4,781 0 24 Feb 2021
Scaling Laws for Neural Language Models Jared Kaplan Sam McCandlish T. Henighan Tom B. Brown B. Chess R. Child Scott Gray Alec Radford Jeff Wu Dario Amodei 258 4,489 0 23 Jan 2020
A Style-Based Generator Architecture for Generative Adversarial Networks Tero Karras S. Laine Timo Aila 285 10,354 0 12 Dec 2018