arXiv Machine Learning July 2, 2026 By Alexander Chemeris, Ming Jin, Randall Balestriero

LeNEPA: No-Augmentation Next-Latent Prediction for Time-Series Representation Learning

Read the original on arXiv Machine Learning →

arXiv:2607. 00958v1 Announce Type: new Abstract: 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 depends on view and augmentation choices that encode domain-specific invariances.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jul 21

A Framework for Early Sepsis Prediction via Self-Supervised (JEPA) and Federated Representation Learning

arXiv:2607. 16681v1 Announce Type: new Abstract: Early sepsis prediction from electronic health records is challenged by irregular sampling, high missingness, and class imbalance.

By Umair bin Mansoor, Munaf Rashid, Roomi Naqvi

rag fine-tuning efficiency benchmarks

arXiv AI

Jul 9

TimEE: End-to-end Time Series Classification via In-Context Learning

arXiv:2607. 07500v1 Announce Type: cross Abstract: Time series classification (TSC) is dominated by a two-stage paradigm: train a feature encoder -- either from scratch on the target dataset or via pretraining on large corpora -- and then fit a task-specific classifier on top.

By Jaris K\"uken, Shi Bin Hoo, Martin Mr\'az, Frank Hutter, Lennart Purucker

llms benchmarks

arXiv Machine Learning

Jun 2

Amortized Predictability-aware Training Framework for Time Series Forecasting and Classification

arXiv:2602. 16224v2 Announce Type: replace Abstract: Time series data are prone to noise in various domains, and training samples may contain low-predictability patterns that deviate from the normal data distribution, leading to training instability or convergence to poor local minima.

By Xu Zhang, Peng Wang, Yichen Li, Wei Wang

safety

arXiv Machine Learning

Jun 8

CF-JEPA: Mask-free forward prediction with asymmetric encoder utilization for time-series representation learning

arXiv:2606. 07031v1 Announce Type: new Abstract: Self-supervised learning (SSL) for time-series representation learning is dominated by two paradigms: contrastive methods, which face challenges in constructing positive or negative pairs, and masking-based methods, which disrupt the temporal continuity of time-series signals.

By Jaehoon Lee, Sunghyun Sim

llms rag benchmarks

arXiv AI

Jun 18

Clin-JEPA: A Multi-Phase Co-Training Framework for Joint-Embedding Predictive Pretraining on EHR Patient Trajectories

arXiv:2605. 10840v3 Announce Type: replace-cross Abstract: We present Clin-JEPA, a multi-phase co-training framework for joint-embedding predictive (JEPA) pretraining on EHR patient trajectories.

By Yixuan Yang, Mehak Arora, Ryan Zhang, Baraa Abed, Junseob Kim, Tilendra Choudhary, Md Hassanuzzaman, Kevin Zhu, Ayman Ali, Chengkun Yang, Alasdair Edward Gent, Victor Moas, Rishikesan Kamaleswaran

rag diffusion robotics fine-tuning safety

arXiv Machine Learning

Jul 22

A Better Start for Language Models: Domain-Conditional Position Offsets

arXiv:2607. 18302v1 Announce Type: new Abstract: Autoregressive language models are least accurate at the beginning of a sequence, where little context forces reliance on a generic pretraining prior.

By Ye Qiao

llms rag fine-tuning safety

Related stories

A Framework for Early Sepsis Prediction via Self-Supervised (JEPA) and Federated Representation Learning

TimEE: End-to-end Time Series Classification via In-Context Learning

Amortized Predictability-aware Training Framework for Time Series Forecasting and Classification

CF-JEPA: Mask-free forward prediction with asymmetric encoder utilization for time-series representation learning

Clin-JEPA: A Multi-Phase Co-Training Framework for Joint-Embedding Predictive Pretraining on EHR Patient Trajectories

A Better Start for Language Models: Domain-Conditional Position Offsets