The Year in AI Papers
The year/Topics/Robot policies

Research collection

Robot policies

Vision-language-action models, robot manipulation and navigation policies, embodied control, and robot learning from demonstration or simulation.

Papers
59
Research labs
2
Official code
45

51–59 of 59 papers in this collection

51

arXiv.org

Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model

The paper introduces Spatial Forcing (SF), a method to enhance the spatial awareness of Vision-Language-Action (VLA) models without explicit 3D inputs. VLA models, built on 2D-pretrained VLMs, lack 3D understanding, limiting their robotic manipulation performance. Existing solutions using depth sensors or point clouds face issues like sensor noise and data…

Fuhao Li, Wenxuan Song, Han Zhao, Jingbo Wang, et al.
Published
Oct 2025
Citations
93
Code
277 stars
Read summary Original
52

arXiv.org

D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI

The paper introduces D2E, a framework that uses desktop interactions (screen, keyboard, mouse) as a pretraining substrate for embodied AI. It comprises three components: the OWA Toolkit for scalable data collection and compression (152x), the Generalist-IDM for pseudo-labeling YouTube videos via timestamp-based next-event prediction (NEP-tau), and VAPT for…

Suhwan Choi, Jaeyoon Jung, Haebin Seong, Minchan Kim, et al.
Published
Oct 2025
Citations
0
Code
90 stars
Read summary Original
53

IEEE International Conference on Computer Vision

StealthAttack: Robust 3D Gaussian Splatting Poisoning via Density-Guided Illusions

The paper introduces StealthAttack, the first data poisoning attack targeting 3D Gaussian Splatting (3DGS) to inject view-dependent illusory objects. The method uses Kernel Density Estimation (KDE) to identify low-density regions in the Gaussian point cloud, placing poison points along rays from the target (poisoned) view to make illusions visible only…

Bo-Hsu Ke, You-Zhe Xie, Yu-Lun Liu, Wei-Chen Chiu
Published
Oct 2025
Citations
6
Code
64 stars
Read summary Original
54

arXiv.org

VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulators

VLA-RFT is a reinforcement fine-tuning framework for Vision-Language-Action (VLA) models that uses a data-driven world model as a simulator to provide verified rewards, avoiding costly real-world interactions and sim-to-real gaps. The world model, pretrained on offline data, predicts future visual observations conditioned on actions, enabling policy…

Hengtao Li, Pengxiang Ding, Runze Suo, Yihao Wang, et al.
Published
Oct 2025
Citations
50
Code
163 stars
Read summary Original
55

AAAI Conference on Artificial Intelligence

VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model

VLA-Adapter is a novel paradigm for Vision-Language-Action (VLA) models that reduces reliance on large-scale VLMs and extensive pre-training. It systematically analyzes which vision-language (VL) conditions are essential for bridging perception to action, finding that middle-layer raw features and deep-layer ActionQuery features are most effective, and…

Yihao Wang, Pengxiang Ding, Lingxiao Li, Can Cui, et al.
Published
Sep 2025
Citations
129
Code
2.3K stars
Read summary Original
56

arXiv.org

Robix: A Unified Model for Robot Interaction, Reasoning and Planning

Robix is a unified vision-language model that integrates robot reasoning, task planning, and natural language interaction within a single architecture, serving as the high-level cognitive layer in a hierarchical robot system. It generates atomic commands for a low-level controller and verbal responses for humans, enabling complex instruction following,…

Huang Fang, Mengxi Zhang, Heng Dong, Wei Li, et al.
Published
Sep 2025
Citations
21
Code
Not linked
Read summary Original
57

Independent research

EO-1: An Open Unified Embodied Foundation Model for General Robot Control

The paper introduces EO-Robotics, comprising the EO-1 model and the EO-Data1.5M dataset, to advance general robot control. EO-1 is a 3B-parameter unified embodied foundation model that integrates multimodal understanding and robot action generation in a single decoder-only transformer, combining autoregressive decoding for text with flow-matching denoising…

Delin Qu, Haoming Song, Qizhi Chen, Zhaoqing Chen, et al.
Published
Aug 2025
Citations
21
Code
292 stars
Read summary Original
58

arXiv.org

Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation

Genie Envisioner (GE) is a unified world foundation platform for robotic manipulation, integrating policy learning, evaluation, and simulation within a video-generative framework. GE-Base, an instruction-conditioned multi-view video diffusion model, is pretrained on ~3,000 hours of data from one million real-world episodes (AgiBot-World-Beta) to capture…

Yue Liao, Pengfei Zhou, Siyuan Huang, Donglin Yang, et al.
Published
Aug 2025
Citations
113
Code
568 stars
Read summary Original
59

AAAI Conference on Artificial Intelligence

DeepPHY: Benchmarking Agentic VLMs on Physical Reasoning

DeepPHY is a benchmark framework for evaluating interactive physical reasoning in agentic Vision-Language Models (VLMs). It integrates six physics-based simulation environments: PHYRE, I-PHYRE, Kinetix, Pooltool, Angry Birds, and Cut the Rope, converting continuous action spaces into discrete, structured formats and augmenting observations with…

Xinrun Xu, Pi Bu, Ye Wang, Börje F. Karlsson, et al.
Published
Aug 2025
Citations
10
Code
172 stars
Read summary Original