DexTeleop-0 enhances bimanual teleoperation with tactile feedback, achieving higher task success rates.

Haichao Liu, Yuyao Jiang, Hyunsun Park et al.

Humanoid-OmniOcc: A stereo-based panoramic occupancy dataset enhancing robot navigation safety.

Xianda Guo, Bohao Zhang, Chenwei Huang et al.

PanoVine uses 19 cameras for whole-body visuomotor control of soft vine robots.

Yimeng Qin, Xiaomeng Xu, William Heap et al.

Wh0 framework uses generative video world models to create a 50k human-hand manipulation dataset, boosting VLA model zero-shot success to 38.9%.

Yangtao Chen, Zixuan Chen, Peiyang Wang et al.

DUET leverages human demonstration pretraining with Action Chunking Transformer to enhance heterogeneous dual-robot collaboration, achieving 20% higher success rates.

Yiqi Zhao, Ruohai Ge, Celina Shiyu Wang et al.

Vesta unifies localization, navigation, reasoning, and planning in a single model, outperforming state-of-the-art baselines by over 20%.

Johan Bjorck, Zhiqi Li, Yunze Man et al.

Integrating Genetic Algorithm and A* with AHP for multi-criteria path planning enhances continuum robot resilience by increasing path diversity and robustness.

Oxana Shamilyan, Ievgen Kabin, Zoya Dyka et al.

Proposes ARC: a unified block-coordinate descent framework combining adaptive robust loss, IRLS, and MWCD for joint state and covariance estimation, robust against outliers and non-Gaussian noise, with automatic parameter tuning.

Alexandre Hadji-Thomas, Andrew Stirling, James R. Forbes

Proposes DO AS I DO framework that reconstructs human hand-object interactions from monocular RGB videos and retargets them to dexterous robots, outperforming state-of-the-art methods.

Bhawna Paliwal, Haritheja Etukuru, William Liang et al.

Analyzes observability and consistency of VINS with anchored feature parameterization, demonstrating improved estimator reliability through theoretical and experimental validation.

Mitchell Cohen, Vassili Korotkine, James Richard Forbes

WalkOCC uses hybrid 2D-3D learning for monocular 3D occupancy prediction, achieving a 15.6% mIoU improvement on Sidewalk3D.

Yukai Ma, Joe Lin, Liu Liu et al.

VERITAS framework uses inference-time verification with visual models to improve robot policies by 10% success rate without additional training.

Mingtong Zhang, Dhruv Shah

Qwen-RobotManip introduces a unified alignment framework enabling large-scale multi-robot pretraining, achieving zero-shot instruction following and cross-embodiment transfer, surpassing SOTA.

Haoqi Yuan, Zhixuan Liang, Anzhe Chen et al.

EgoInfinity is a modular web-scale 4D hand-object interaction engine that automatically extracts high-quality data from internet videos for robot retargeting and learning.

Gaotian Wang, Kejia Ren, Andrew Morgan et al.

ACE-EGO-0 unifies human and robot data via spatial, structural, and temporal alignment for VLA pretraining, boosting manipulation performance.

Hao Li, Ganlong Zhao, Yufei Liu et al.

R2RDreamer enhances 2D manipulation policies' spatial generalization via 3D-aware augmentation and occlusion-aware video completion, achieving significant performance gains with limited demonstrations.

Xiuwei Xu, Haowen Sun, Angyuan Ma et al.

BinTrack uses trajectory-based binary search to improve open-source spatial QA accuracy by 22.8%.

Dongbin Na, Chanwoo Kim, Soonbin Rho et al.

ART-Glove integrates 16 rigid functional surfaces and 22-DoF joint sensing with 2048-taxel tactile arrays, enabling contact-grounded dexterous demonstration capture at 120Hz.

Changyi Lin, Ding Zhao

TopoRetarget enhances RL policy training success by 40.6% by preserving hand-object interaction.

Jielin Wu, Shenzhe Yao, Guanqi He et al.

LaWAM uses latent visual subgoals for efficient scene prediction, achieving 98.6% success with 187ms inference.

Jialei Chen, Kai Wang, Kang Chen et al.