English
Related papers

Related papers: ForTIFAI: Fending Off Recursive Training Induced F…

200 papers

Despite the huge progress in myriad generation tasks, pretrained language models (LMs) such as GPT2 still tend to generate repetitive texts with maximization-based decoding algorithms for open-ended generation. We attribute their…

Computation and Language · Computer Science 2023-07-06 Jian Guan , Minlie Huang

As Large Language Models (LLMs) become increasingly prevalent, their generated outputs are proliferating across the web, risking a future where machine-generated content dilutes human-authored text. Since online data is the primary resource…

Computation and Language · Computer Science 2025-09-23 George Drayson , Emine Yilmaz , Vasileios Lampos

As artificial intelligence (AI) becomes more widely used, concerns are growing that model collapse could lead to knowledge collapse, i.e. a degradation to a narrow and inaccurate set of ideas. Prior work has demonstrated single-model…

Machine Learning · Computer Science 2026-03-16 Damian Hodel , Jevin D. West

Trained on massive amounts of human-generated content, AI-generated image synthesis is capable of reproducing semantically coherent images that match the visual appearance of its training data. We show that when retrained on even small…

Artificial Intelligence · Computer Science 2025-04-01 Matyas Bohacek , Hany Farid

Recent advancements in large-scale generative models have enabled the creation of high-quality images and videos, but have also raised significant safety concerns regarding the generation of unsafe content. To mitigate this, concept erasure…

Computer Vision and Pattern Recognition · Computer Science 2025-11-26 Viet Nguyen , Vishal M. Patel

AI training datasets will inevitably contain AI-generated examples, leading to ``feedback'' in which the output of one model impacts the training of another. It is known that such iterative feedback can lead to model collapse, yet the…

Machine Learning · Computer Science 2026-02-24 Vibhas Kumar Vats , David J. Crandall , Samuel Goree

In many real-world scenarios, data to train machine learning models becomes available over time. Unfortunately, these models struggle to continually learn new concepts without forgetting what has been learnt in the past. This phenomenon is…

Computation and Language · Computer Science 2023-01-16 Beyza Ermis , Giovanni Zappella , Martin Wistuba , Aditya Rawal , Cedric Archambeau

Data heterogeneity is an inherent challenge that hinders the performance of federated learning (FL). Recent studies have identified the biased classifiers of local models as the key bottleneck. Previous attempts have used classifier…

Machine Learning · Computer Science 2023-08-29 Zexi Li , Xinyi Shang , Rui He , Tao Lin , Chao Wu

Catastrophic forgetting is a major problem in continual learning, and lots of approaches arise to reduce it. However, most of them are evaluated through task accuracy, which ignores the internal model structure. Recent research suggests…

Machine Learning · Computer Science 2026-03-06 Yunqin Zhu , Jun Jin

Federated Learning (FL) aims at unburdening the training of deep models by distributing computation across multiple devices (clients) while safeguarding data privacy. On top of that, Federated Continual Learning (FCL) also accounts for data…

Machine Learning · Computer Science 2025-05-27 Riccardo Salami , Pietro Buzzega , Matteo Mosconi , Mattia Verasani , Simone Calderara

In real-world applications, learning-enabled systems often undergo iterative model development to address challenging or emerging tasks, which involve collecting new data, training a new model and validating the model. This continual model…

Machine Learning · Computer Science 2025-04-22 Gang Li , Wendi Yu , Yao Yao , Wei Tong , Yingbin Liang , Qihang Lin , Tianbao Yang

Deep learning models are prone to forgetting information learned in the past when trained on new data. This problem becomes even more pronounced in the context of federated learning (FL), where data is decentralized and subject to…

Machine Learning · Computer Science 2023-07-19 Sara Babakniya , Zalan Fabian , Chaoyang He , Mahdi Soltanolkotabi , Salman Avestimehr

Exemplar-Free Class Incremental Learning (EFCIL) tackles the problem of training a model on a sequence of tasks without access to past data. Existing state-of-the-art methods represent classes as Gaussian distributions in the feature…

Machine Learning · Computer Science 2024-10-29 Grzegorz Rypeść , Sebastian Cygert , Tomasz Trzciński , Bartłomiej Twardowski

As synthetic data becomes higher quality and proliferates on the internet, machine learning models are increasingly trained on a mix of human- and machine-generated data. Despite the successful stories of using synthetic data for…

Machine Learning · Computer Science 2024-06-11 Nate Gillman , Michael Freeman , Daksh Aggarwal , Chia-Hong Hsu , Calvin Luo , Yonglong Tian , Chen Sun

The sequential nature of modern LLMs makes them expensive and slow, and speculative sampling has proven to be an effective solution to this problem. Methods like EAGLE perform autoregression at the feature level, reusing top-layer features…

Computation and Language · Computer Science 2025-04-24 Yuhui Li , Fangyun Wei , Chao Zhang , Hongyang Zhang

We present the Tamed Cross Entropy (TCE) loss function, a robust derivative of the standard Cross Entropy (CE) loss used in deep learning for classification tasks. However, unlike other robust losses, the TCE loss is designed to exhibit the…

Machine Learning · Computer Science 2018-10-12 Manuel Martinez , Rainer Stiefelhagen

Tools serve as pivotal interfaces that enable humans to understand and reshape the environment. With the advent of foundation models, AI systems can utilize tools to expand their capabilities and interact with the real world. Existing tool…

Computation and Language · Computer Science 2024-03-15 Shuofei Qiao , Honghao Gui , Chengfei Lv , Qianghuai Jia , Huajun Chen , Ningyu Zhang

The current paradigm of training deep neural networks for classification tasks includes minimizing the empirical risk that pushes the training loss value towards zero, even after the training error has been vanished. In this terminal phase…

Machine Learning · Computer Science 2024-06-07 Hien Dang , Tho Tran , Tan Nguyen , Nhat Ho

Explainable AI (XAI) aims to provide insights into the decisions made by AI models. To date, most XAI approaches provide only one-time, static explanations, which cannot cater to users' diverse knowledge levels and information needs.…

Human-Computer Interaction · Computer Science 2025-03-24 Tong Zhang , Mengao Zhang , Wei Yan Low , X. Jessie Yang , Boyang Li

Achieving backward compatibility when rolling out new models can highly reduce costs or even bypass feature re-encoding of existing gallery images for in-production visual retrieval systems. Previous related works usually leverage losses…

Computer Vision and Pattern Recognition · Computer Science 2021-08-05 Qiang Meng , Chixiang Zhang , Xiaoqiang Xu , Feng Zhou