arXiv Machine Learning August 7, 2026 By Zihan Zhou, Qifu Wen, Xi Zeng

SR-JEPA: Learning Predictive Latent State in 3D Scenes

Read the original on arXiv Machine Learning →

arXiv:2608. 05774v1 Announce Type: cross Abstract: Joint-embedding predictive architectures learn by predicting latent representations of missing observations, yet many masked JEPAs are evaluated primarily through the encoders they produce.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Sep 1

Does Latent Planning Survive Point Clouds? Action-Conditioned JEPA World Models for Geometric Observations

arXiv:2608.29434v1 Announce Type: cross Abstract: JEPA world models make latent-space planning a practical route to control, but they are built almost exclusively on images. Whether latent prediction...

By Fabio F. Oberweger, Michael Schwingshackl

benchmarks

arXiv AI

Jul 2

Cross4D-JEPA: Dense Cross-modal Correspondence Distillation for 4D Point Cloud Representation Learning

arXiv:2607. 00514v1 Announce Type: cross Abstract: Automatic understanding of dynamic 4D point clouds, the 3D-point sequences captured over time by depth sensors and LiDAR, is central to robotics and embodied perception.

By Trung Thanh Nguyen, Hai Nguyen-Truong, Tu Vo, Hoang M. Truong, Tuan-Anh Vu

rag diffusion robotics fine-tuning efficiency multimodal benchmarks

arXiv Computer Vision

4d ago

PGL-3D: Towards Progressive Geometric Learning for 3D Visual Query Localization

PGL-3D introduces a progressive geometric learning framework for 3D visual query localization, where intermediate cuboids guide feature aggregation and refinement. The method predicts a complete cuboid for each proposal, selects reference observations via Query‑Tube‑Memory, pools query‑conditioned features, and re‑predicts refined cuboids. A training‑only objective, ST‑D9O, supervises cuboid geometry at every stage, yielding significant performance gains over prior baselines.

By Liang Peng, Shizhuo Mu, Bohan Tan, Wenyuan Wang, Chen Zhao, Xingping Dong, Heng Fan, Libo Zhang, Bo Du

benchmarks

arXiv Computer Vision

Sep 23

DinoComplete: 3D Shape Completion with Distilled Semantic Priors and State Space Models

arXiv:2605.26949v2 Announce Type: replace Abstract: 3D shape completion from partial scans remains challenging for unseen categories and noisy real-world observations, where geometry alone is often i...

By Furkan Mert Algan, Eckehard Steinbach

arXiv Computer Vision

6d ago

GraphWrit3R: End-to-End 3D Scene Graph Writing

arXiv:2609.31595v1 Announce Type: new Abstract: 3D scene graphs provide a structured representation of complex environments by encoding objects, their semantic attributes, and the spatial and functio...

By Luka Milivojevic, Nikola Popovic, Sayan Deb Sarkar, Sebastian Koch, Iro Armeni, Luc Van Gool, Danda Pani Paudel

llms benchmarks safety

arXiv Machine Learning

Aug 26

Joint-Embedding Prediction of Masked Point Tubes for Self-Supervised Learning on 4D Point Cloud Videos

arXiv:2608.24093v1 Announce Type: cross Abstract: Self-supervised representation learning for 4D point cloud videos is challenging because annotations are costly and reconstruction-based pretraining...

By Jheng-Ling Lee, Shang-Tse Chen

rag fine-tuning benchmarks

One email a morning, machine-written

Related stories

Does Latent Planning Survive Point Clouds? Action-Conditioned JEPA World Models for Geometric Observations

Cross4D-JEPA: Dense Cross-modal Correspondence Distillation for 4D Point Cloud Representation Learning

PGL-3D: Towards Progressive Geometric Learning for 3D Visual Query Localization

DinoComplete: 3D Shape Completion with Distilled Semantic Priors and State Space Models

GraphWrit3R: End-to-End 3D Scene Graph Writing

Joint-Embedding Prediction of Masked Point Tubes for Self-Supervised Learning on 4D Point Cloud Videos