19 citations · 27 across the 20 of their papers we have counts for
24 papers
Towards Financial World Modeling
Humzah Merchant, Alec Guthrie, Simon Mahns +2
Building a world model requires a state representation useful for planning and decision-making---potentially over tasks unknown at training time. In the context of financial market…
LeNEPA: No-Augmentation Next-Latent Prediction for Time-Series Representation Learning
Alexander Chemeris, Ming Jin, Randall Balestriero
Time series are central to modern data mining applications, from industrial telemetry and server metrics to finance and physiology, yet time-series self-supervised learning often d…
Aionoscope: Debugging Latent-State Accessibility in Time-Series Representations
Alexander Chemeris, Ming Jin, Randall Balestriero
Time-series models are often evaluated by what they can forecast or classify, but those scores do not show whether their representations preserve the process state a user may want…
VISReg: Variance-Invariance-Sketching Regularization for JEPA training
Haiyu Wu, Randall Balestriero, Morgan Levine
Self-supervised learning methods prevent embedding collapse via modeling heuristics or explicit regularization of the embedding space. Among the latter, VICReg decomposes regulariz…
stable-pretraining-v1: Foundation Model Research Made Simple
Randall Balestriero, Hugues Van Assel, Sami BuGhanem +1
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…
MapSAM2: Adapting SAM2 for Automatic Segmentation of Historical Map Images and Time Series
Xue Xia, Randall Balestriero, Tao Zhang +4
Historical maps are unique and valuable archives that document geographic features across different time periods. However, automated analysis of historical map images remains a sig…
Position: An Empirically Grounded Identifiability Theory Will Accelerate Self-Supervised Learning Research
Patrik Reizinger, Randall Balestriero, David Klindt +1
Self-Supervised Learning (SSL) powers many current AI systems. As research interest and investment grow, the SSL design space continues to expand. The Platonic view of SSL, followi…
Eidetic Learning: an Efficient and Provable Solution to Catastrophic Forgetting
Nicholas Dronen, Randall Balestriero
Catastrophic forgetting -- the phenomenon of a neural network learning a task t1 and losing the ability to perform it after being trained on some other task t2 -- is a long-standin…
Beyond and Free from Diffusion: Invertible Guided Consistency Training
Chia-Hong Hsu, Shiu-hong Kao, Randall Balestriero
Guidance in image generation steers models towards higher-quality or more targeted outputs, typically achieved in Diffusion Models (DMs) via Classifier-free Guidance (CFG). However…
No Location Left Behind: Measuring and Improving the Fairness of Implicit Representations for Earth Data
Daniel Cai, Randall Balestriero
Implicit neural representations (INRs) exhibit growing promise in addressing Earth representation challenges, ranging from emissions monitoring to climate modeling. However, existi…
Curvature Tuning: Provable Training-free Model Steering From a Single Parameter
Leyang Hu, Matteo Gamba, Randall Balestriero
The scaling of model and data sizes has reshaped the AI landscape, establishing finetuning pretrained models as the standard paradigm for solving downstream tasks. However, dominan…
Beyond [cls]: Exploring the true potential of Masked Image Modeling representations
Marcin Przewięźlikowski, Randall Balestriero, Wojciech Jasiński +2
Masked Image Modeling (MIM) has emerged as a promising approach for Self-Supervised Learning (SSL) of visual representations. However, the out-of-the-box performance of MIMs is typ…
Self-supervised Video Instance Segmentation Can Boost Geographic Entity Alignment in Historical Maps
Xue Xia, Randall Balestriero, Tao Zhang +1
Tracking geographic entities from historical maps, such as buildings, offers valuable insights into cultural heritage, urbanization patterns, environmental changes, and various his…
The Fair Language Model Paradox
Andrea Pinto, Tomer Galanti, Randall Balestriero
Large Language Models (LLMs) are widely deployed in real-world applications, yet little is known about their training dynamics at the token level. Evaluation typically relies on ag…
ALLoRA: Adaptive Learning Rate Mitigates LoRA Fatal Flaws
Hai Huang, Randall Balestriero
Low-Rank Adaptation (LoRA) is the bread and butter of Large Language Model (LLM) finetuning. LoRA learns an additive low-rank perturbation, , of a pretrained matrix parameter $…
Self-Supervised Anomaly Detection in the Wild: Favor Joint Embeddings Methods
Daniel Otero, Rafael Mateus, Randall Balestriero
Accurate anomaly detection is critical in vision-based infrastructure inspection, where it helps prevent costly failures and enhances safety. Self-Supervised Learning (SSL) offers…
Cross-Entropy Is All You Need To Invert the Data Generating Process
Patrik Reizinger, Alice Bizeul, Attila Juhos +4
Supervised learning has become a cornerstone of modern machine learning, yet a comprehensive theory explaining its effectiveness remains elusive. Empirical phenomena, such as neura…
GPS-SSL: Guided Positive Sampling to Inject Prior Into Self-Supervised Learning
Aarash Feizi, Randall Balestriero, Adriana Romero-Soriano +1
We propose Guided Positive Sampling Self-Supervised Learning (GPS-SSL), a general method to inject a priori knowledge into Self-Supervised Learning (SSL) positive samples selection…
Multi-scale clustering and source separation of InSight mission seismic data
Ali Siahkoohi, Rudy Morel, Randall Balestriero +4
Unsupervised source separation involves unraveling an unknown set of source signals recorded through a mixing operator, with limited prior knowledge about the sources, and only acc…
FAIR-Ensemble: When Fairness Naturally Emerges From Deep Ensembling
Wei-Yin Ko, Daniel D'souza, Karina Nguyen +2
Ensembling multiple Deep Neural Networks (DNNs) is a simple and effective way to improve top-line metrics and to outperform a larger single model. In this work, we go beyond top-li…
Unsupervised Learning on a DIET: Datum IndEx as Target Free of Self-Supervision, Reconstruction, Projector Head
Randall Balestriero
Costly, noisy, and over-specialized, labels are to be set aside in favor of unsupervised learning if we hope to learn cheap, reliable, and transferable models. To that end, spectra…
SymJAX: symbolic CPU/GPU/TPU programming
Randall Balestriero
SymJAX is a symbolic programming version of JAX simplifying graph input/output/updates and providing additional functionalities for general machine learning and deep learning appli…
Multiscale Residual Mixture of PCA: Dynamic Dictionaries for Optimal Basis Learning
Randall Balestriero
In this paper we are interested in the problem of learning an over-complete basis and a methodology such that the reconstruction or inverse problem does not need optimization. We a…
Neural Decision Trees
Randall Balestriero
In this paper we propose a synergistic melting of neural networks and decision trees (DT) we call neural decision trees (NDT). NDT is an architecture a la decision tree where each…