arXiv Computer Vision October 9, 2026 By Skand Peri, Hung Nguyen, Chanho Kim, Li Fuxin, Stefan Lee

3D Point World Models: Point Completion Enables More Accurate Dynamics Learning

Read the original on arXiv Computer Vision →

The paper introduces 3D Point World Models (3DPWM), a task‑agnostic world model that completes partial point clouds before learning action‑conditioned dynamics in 3D space. By operating on fully reconstructed geometry, 3DPWM achieves reliable long‑horizon rollouts (100–300+ steps) and accurate cost evaluation for model‑based planning. Experiments on various robotic embodiments and tabletop manipulation tasks show that 3DPWM supports both open‑loop and closed‑loop planning and enables successful sim‑to‑real transfer.

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 Computer Vision.

arXiv Computer Vision

Sep 17

PointZero: 3D Point Track Completion for Learning Transferable 3D Dynamics

arXiv:2609.19142v1 Announce Type: new Abstract: World models endow perceptual systems with the ability to predict how scenes evolve under interaction. They are most beneficial when trained on diverse...

By Bardienus P. Duisterhof, Kaifeng Zhang, Adam Hung, Bowen Wen, Stan Birchfield, Yunzhu Li, Deva Ramanan, Jeffrey Ichnowski

llms robotics fine-tuning benchmarks

Hugging Face Trending Papers

Sep 16

PointZero: 3D Point Track Completion for Learning Transferable 3D Dynamics

World models endow perceptual systems with the ability to predict how scenes evolve under interaction. They are most beneficial when trained on diverse volumes of data, to instill a rich prior into do...

llms robotics fine-tuning benchmarks

arXiv Computer Vision

Sep 3

Spatially Aware World Action Model via Geometric Latent Diffusion

The paper introduces Spatially Aware World Action Model (SA‑WAM), a diffusion‑based framework that extends existing World Action Models by incorporating depth information alongside RGB to enable 3‑D‑aware action and future‑state prediction. SA‑WAM repurposes a pretrained video diffusion model, using a nonlinear encoding to map unbounded depth into the tokenizer’s bounded domain, thus preserving pretrained visual priors without 3‑D‑specific fine‑tuning. The model achieves state‑of‑the‑art performance on RoboCasa and LIBERO‑Plus benchmarks and demonstrates superior real‑world performance on a UR5 robotic arm in randomized environments, while also providing analysis linking world‑model prediction quality to rollout success.

By Javier Alejandro Lopetegui Gonzalez, Paul Pacaud, Cordelia Schmid

diffusion nlp robotics fine-tuning benchmarks

arXiv AI

Jun 9

Unifying Object-Centric World Models and Diffusion Policy: A Hierarchical Framework for Multi-Stage Robotic Tasks

arXiv:2606. 08775v1 Announce Type: cross Abstract: Visual world models have shown great potential in learning complex system dynamics.

By Raktim Gautam Goswami, Prashanth Krishnamurthy, Yann LeCun, Farshad Khorrami

diffusion robotics benchmarks

arXiv Machine Learning

Jun 4

PointAction: 3D Points as Universal Action Representations for Robot Control

arXiv:2606. 03943v1 Announce Type: cross Abstract: Video-Action Models (VAMs) leverage the broad visual dynamics captured by pre-trained video diffusion models, offering a promising path toward generalizable robot manipulation.

By Mutian Tong, Han Jiang, Qiao Feng, Lingjie Liu, Jiatao Gu

diffusion robotics benchmarks

arXiv AI

Jul 1

3D HAMSTER: Bridging Planning and Control in Hierarchical Vision Language Action Models through 3D Trajectory Guidance

arXiv:2606. 31329v1 Announce Type: cross Abstract: Hierarchical Vision-Language-Action (VLA) models decouple high-level planning from low-level control to improve generalization in robot manipulation.

By Dongyoon Hwang, Byungkun Lee, Dongjin Kim, Hyojin Jang, Hoiyeong Jin, Jueun Mun, Minho Park, Hojoon Lee, Hyunseung Kim, Jaegul Choo

llms robotics multimodal benchmarks

One email a morning, machine-written

Related stories

PointZero: 3D Point Track Completion for Learning Transferable 3D Dynamics

PointZero: 3D Point Track Completion for Learning Transferable 3D Dynamics

Spatially Aware World Action Model via Geometric Latent Diffusion

Unifying Object-Centric World Models and Diffusion Policy: A Hierarchical Framework for Multi-Stage Robotic Tasks

PointAction: 3D Points as Universal Action Representations for Robot Control

3D HAMSTER: Bridging Planning and Control in Hierarchical Vision Language Action Models through 3D Trajectory Guidance