paper-with-me

Papers

stable-pretraining-v1: Foundation Model Research Made Simple

2025-11-23 · Randall Balestriero, Hugues Van Assel, Sami BuGhanem, Lucas Maes arxiv

Foundation models and self-supervised learning (SSL) have become central to modern AI, yet research in this area remains hindered by complex codebases, redundant re-implementations, and the heavy engineering burden of scaling experiments. We present stable-pretraining, a modular, extensible, and performance-optimized library built on top of PyTorch, Lightning, Hugging Face, and TorchMetrics. Unlike prior toolkits focused narrowly on reproducing state-of-the-art results, stable-pretraining is designed for flexibility and iteration speed: it unifies essential SSL utilities--including probes, collapse detection metrics, augmentation pipelines, and extensible evaluation routines--within a coherent and reliable framework. A central design principle is logging everything, enabling fine-grained visibility into training dynamics that makes debugging, monitoring, and reproducibility seamless. We validate the library by demonstrating its ability to generate new research insights with minimal overhead, including depthwise representation probing and the analysis of CLIP degradation under synthetic data finetuning. By lowering barriers to entry while remaining scalable to large experiments, stable-pretraining aims to accelerate discovery and expand the possibilities of foundation model research.

📄 PDF Abstract BibTeX arXiv:2511.19484

Code (0)

등록된 구현이 없습니다.

Tasks

Self-Supervised Learning

Similar Papers 제목 키워드 기반

DIET-CP: Lightweight and Data Efficient Self Supervised Continued Pretraining

2025-09-02 · Bryan Rodas, Natalie Montesino, Jakob Ambsdorf, David Klindt 외 arxiv

Continued pretraining offers a promising solution for adapting foundation models to a new target domain. However, in specialized domains, available datasets are often very small, limiting the applicability of SSL methods…

TAP-CT: 3D Task-Agnostic Pretraining of Computed Tomography Foundation Models

2025-11-30 · Tim Veenboer, George Yiasemis, Eric Marcus, Vivien Van Veldhuizen 외 arxiv

Existing foundation models (FMs) in the medical domain often require extensive fine-tuning or rely on training resource-intensive decoders, while many existing encoders are pretrained with objectives biased toward specif…

Speedrunning Tabular Foundation Model Pretraining

2026-06-02 · Salih Bora Ozturk, Alexander Pfefferle, Frank Hutter arxiv

Pretraining cost is a major bottleneck for research on tabular foundation models, slowing the iteration cycle for new architectures, priors, and optimization ideas. Yet the community lacks a simple way to compare and acc…

Mix, Don't Pick: Why Synthetic Corpus Composition Matters for Time Series Foundation Model Pretraining

2026-06-06 · Aaryan Nagpal, Debdeep Sanyal, Murari Mandal, Dhruv Kumar 외 arxiv

Choosing the wrong synthetic generator for time-series foundation model pretraining is costly: under identical training budgets, the best and worst generators produce up to a $2\times$ gap in forecasting error, yet the f…

Foundation Inference Models for Ordinary Differential Equations

2026-02-09 · Maximilian Mauel, Johannes R. Hübers, David Berghaus, Patrick Seifner 외 arxiv

Ordinary differential equations (ODEs) are central to scientific modelling, but inferring their vector fields from noisy trajectories remains challenging. Current approaches such as symbolic regression, Gaussian process …