English
Related papers

Related papers: A Theoretical Perspective: How to Prevent Model Co…

200 papers

Large language models (LLMs) are increasingly used as decision-support tools in data-constrained scientific workflows, where correctness and validity are critical. However, evaluation practices often emphasize stability or reproducibility…

Machine Learning · Computer Science 2026-03-18 Nazia Riasat

Generative artificial intelligence is rapidly transforming the supply side of training data: an increasing share of new tokens, images, and structured records is produced by previous-generation models rather than by human originators.…

General Economics · Economics 2026-05-21 Gustav Olaf Yunus Laitinen-Fredriksson Lundström-Imanov

Looped Language Models (LoopLMs) enable efficient latent reasoning through depth recurrence, yet exhibit unreliable test-time scaling behavior: performance often peaks at a certain iteration depth and then collapses with further recurrence.…

Machine Learning · Computer Science 2026-05-27 Xiao-Wen Yang , Ziyu Han , Xi-Hua Zhang , Wen-Da Wei , Jie-Jing Shao , Lan-Zhe Guo , Yu-Feng Li

Model collapse occurs when generative models degrade after repeatedly training on their own synthetic outputs. We study this effect in overparameterized linear regression in a setting where each iteration mixes fresh real labels with…

Machine Learning · Statistics 2026-02-13 Anvit Garg , Sohom Bhattacharya , Pragya Sur

Reinforcement Learning (RL) is crucial for unlocking the complex reasoning capabilities of Diffusion-based Large Language Models (dLLMs). However, applying RL to dLLMs faces unique challenges in efficiency and stability. To address these…

Artificial Intelligence · Computer Science 2026-02-10 Jiawei Liu , Xiting Wang , Yuanyuan Zhong , Defu Lian , Yu Yang

Recent successes of reinforcement learning (RL) in training large reasoning models motivate the question of whether self-training - the process where a model learns from its own judgments - can be sustained within RL. In this work, we study…

Machine Learning · Computer Science 2025-10-10 Sheikh Shafayat , Fahim Tajwar , Ruslan Salakhutdinov , Jeff Schneider , Andrea Zanette

Teams that have trained large Transformer-based models have reported training instabilities at large scale that did not appear when training with the same hyperparameters at smaller scales. Although the causes of such instabilities are of…

Accurate predictions of when a component will fail are crucial when planning maintenance, and by modeling the distribution of these failure times, survival models have shown to be particularly useful in this context. The presented…

Machine Learning · Computer Science 2024-03-28 Olov Holmer , Mattias Krysander , Erik Frisk

The emergence of in-context learning (ICL) in large language models (LLMs) remains poorly understood despite its consistent effectiveness, enabling models to adapt to new tasks from only a handful of examples. To clarify and improve these…

Machine Learning · Computer Science 2025-10-02 Waïss Azizian , Ali Hasan

Large language models (LLMs) achieve strong performance across diverse tasks, largely driven by high-quality web data used in pre-training. However, recent studies indicate this data source is rapidly depleting. Synthetic data emerges as a…

We propose a novel way to integrate control techniques with reinforcement learning (RL) for stability, robustness, and generalization: leveraging contraction theory to realize modularity in neural control, which ensures that combining…

Machine Learning · Computer Science 2023-11-08 Bing Song , Jean-Jacques Slotine , Quang-Cuong Pham

Time-dependent data-generating distributions have proven to be difficult for gradient-based training of neural networks, as the greedy updates result in catastrophic forgetting of previously learned knowledge. Despite the progress in the…

Machine Learning · Computer Science 2023-04-03 Matthias De Lange , Gido van de Ven , Tinne Tuytelaars

Recursive Self-Improvement (RSI) enables intelligence systems to autonomously refine their capabilities. This paper explores the application of RSI in text-to-image diffusion models, addressing the challenge of training collapse caused by…

Computer Vision and Pattern Recognition · Computer Science 2025-02-17 Xulu Zhang , Xiaoyong Wei , Jinlin Wu , Jiaxin Wu , Zhaoxiang Zhang , Zhen Lei , Qing Li

A prevailing narrative in LLM post-training holds that supervised finetuning (SFT) memorizes while reinforcement learning (RL) generalizes. We revisit this claim for reasoning SFT with long chain-of-thought (CoT) supervision and find that…

Artificial Intelligence · Computer Science 2026-04-09 Qihan Ren , Peng Wang , Ruikun Cai , Shuai Shao , Dadi Guo , Yuejin Xie , Yafu Li , Quanshi Zhang , Xia Hu , Jing Shao , Dongrui Liu

The proliferation of AI-generated content online has fueled concerns over \emph{model collapse}, a degradation in future generative models' performance when trained on synthetic data generated by earlier models. Industry leaders, premier…

Machine Learning · Computer Science 2025-03-19 Rylan Schaeffer , Joshua Kazdan , Alvan Caleb Arulandu , Sanmi Koyejo

Lifelong machine learning (LML) is an area of machine learning research concerned with human-like persistent and cumulative nature of learning. LML system's objective is consolidating new information into an existing machine learning model…

Machine Learning · Computer Science 2023-03-01 Sazia Mahfuz

The empirical emergence of neural collapse -- a surprising symmetry in the feature representations of the training data in the penultimate layer of deep neural networks -- has spurred a line of theoretical research aimed at its…

Machine Learning · Computer Science 2025-05-22 Peter Súkeník , Christoph H. Lampert , Marco Mondelli

Current unlearning methods for LLMs optimize on the private information they seek to remove by incorporating it into their fine-tuning data. We argue this not only risks reinforcing exposure to sensitive data, but also fundamentally…

Machine Learning · Computer Science 2026-03-03 Yan Scholten , Sophie Xhonneux , Leo Schwinn , Stephan Günnemann

The deployment of pre-trained perception models in novel environments often leads to performance degradation due to distributional shifts. Although recent artificial intelligence approaches for metacognition use logical rules to…

Despite scale driving substantial recent advancements in machine learning, reinforcement learning (RL) methods still primarily use small value functions. Naively scaling value functions -- including with a transformer architecture, which is…

Machine Learning · Computer Science 2026-02-03 Perry Dong , Kuo-Han Hung , Alexander Swerdlow , Dorsa Sadigh , Chelsea Finn
‹ Prev 1 3 4 5 6 7 10 Next ›