activity
20242026
collaborators

14 papers

cs.LG2026

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…

cs.LG2026

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…

cs.CV2026

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…

cs.LG2026

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…

cs.SE2025

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…

cs.CV2025

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…