Physically-grounded GPU apple-tree simulation using Euler-Bernoulli beams, rupture, and detachment mechanics, enabling autonomous harvesting research.

Humphrey Munn

OTQL integrates advantage-weighted conditional optimal transport with flow models, achieving few-step inference and efficient policy fine-tuning, boosting success rates from 36% to 86%.

Andreas Sochopoulos, Esmeralda S. Whitammer, Nikolaos Tsagkas et al.

This paper introduces GPUSimBench, a benchmark system to evaluate GPU-based robotic simulators' scalability, physical fidelity, and non-determinism, revealing key limitations.

Huzhenyu Zhang, Shenghai Yuan, Wenrui Yan et al.

PRISM generates personalized robotic datasets from a single image and instruction, constructing semantically aligned digital scenes with instance diversity.

Dogyu Ko, Haneul Kim, Chanyoung Yeo et al.

Proposes MECo-WAM, integrating 4D geometric priors during training, boosting manipulation success to 98.2% without increasing inference cost.

Jianjun Zhang, Jian Zhu, Taiyi Su et al.

GeoMoLa learns motion latents by predicting point cloud evolution, achieving SOTA performance with single-view RGB-D input.

Yunchao Zhang, Yijia Weng, Ruizhe Liu et al.

WSA1 employs 3D world-spatial-action joint modeling with only 6K hours of demonstration data, achieving 93% success in RoboTwin2.0 and +20% over SOTA in real tasks.

Jiahao Jiang, Jianing Zhang, Zhenhan Yin et al.

ObjRetarget integrates human videos, polyhedral hand models, and anthropomorphic constraints to achieve high-precision robot motion retargeting.

Yuanchuan Lai, Qing Gao, Ziyan Liang et al.

CoRE-VLA uses conditional routing of experts for scalable and robust vision-language-action modeling, excelling in multi-task and long-horizon tasks.

Haozhe Zhang, Sixian Li, Yifei Zhang et al.

Proposed Unified Hand Action Space (UHAS) enables cross-platform dexterous manipulation; experiments show effective transfer across different hand types.

Luis Felipe Casas, Robert Teal, Keval Shah et al.

Proposes an object-centric continuous semantic field method to enhance robot manipulation generalization.

Zheng Sun, Lerong Zhang, Zhihao Li et al.

AmpAttention boosts multi-view robotic manipulation success rate to 91%, reducing training time by 33.3%.

Jin Yang, Ping Wei, Nanning Zheng

EVA-Client provides a unified deployment, debugging, and data collection framework for embodied policies across multiple robot platforms, integrating various real-time inference strategies.

Heqing Yang, Yang Yi, Liyao Wang et al.

Proposed a hybrid dynamic data collection method, significantly enhancing VLA spatial generalization with a 40% success rate increase.

Jincheng Tang, Yilong Zhu, Zhengyuan Xie et al.

Bridge-WA enhances robotic action success by predicting scene changes, achieving a 9.7% improvement on VLABench.

Yongjie Bai, Hanting Wang, Mingtong Dai et al.

PhysMani combines a physics-principled 3D Gaussian world model with a future-aware action policy model to enhance dynamic object manipulation success rates.

Peng Yun, Shouwang Huang, Hao Li et al.

Introduces H-Tac dataset and TTP pre-training system, enabling cross-robot fine manipulation with 98% success rate.

Chi Zhang, Penglin Cai, Ziheng Xi et al.

RoboWorld combines STEP FORCING with autoregressive video models, achieving 0.989 correlation with real-world robot evaluation.

Byeongguk Jeon, Seonghyeon Ye, JaeHyeok Doo et al.

Unified framework for world and action models integrating visual prediction and decision-making, demonstrated on robotic tasks with 20% performance boost.

Xiaoxiong Zhang, Xiong Zeng, Wei Zhang

Proposes conformalized distance fields via functional prediction for safe motion planning, leveraging low-rank residuals for efficient, field-level safety guarantees.

Jaeuk Shin, Yoonseok Ra, Insoon Yang