WARPED generates wrist-view data from monocular RGB videos, reducing data collection time by 5-8x for robot learning.

Harry Freeman, Chung Hee Kim, George Kantor

OmniUMI enables physically grounded robot learning via human-aligned multimodal interaction, enhancing contact-rich manipulation performance.

Shaqi Luo, Yuanyuan Li, Youhao Hu et al.

AffordGen generates diverse demonstrations using 3D generative models to enhance robot manipulation generalization.

Jiawei Zhang, Kaizhe Hu, Yingqian Huang et al.

Hierarchical VLM-guided semantic-geometric framework improves task-aware bimanual grasping, achieving 88.9% strategy alignment in real-world tests.

Fabian Hahne, Vignesh Prasad, Georgia Chalvatzaki et al.

Sumo method enables quadruped robots to dynamically manipulate through sample-based planning, solving multi-task problems.

John Z. Zhang, Maks Sorokin, Jan Brüdigam et al.

RoboAgent employs capability chaining within a single VLM, decomposing complex embodied tasks into basic vision-language problems, enhancing long-term planning.

Peiran Xu, Jiaqi Zheng, Yadong Mu

EgoVerse unifies large-scale egocentric human demonstration data, enabling cross-embodiment robot learning with 80k episodes, 1965 tasks, and multi-institution collaboration.

Ryan Punamiya, Simar Kareer, Zeyi Liu et al.

TAMEn enhances bimanual manipulation success from 34% to 75% through tactile-aware closed-loop data collection.

Longyan Wu, Jieji Ren, Chenghang Jiang et al.

Proposed AAC algorithm uses action entropy to dynamically adjust chunk size, improving robotic task success rates by 2.3%.

Yuanchang Liang, Xiaobo Wang, Kai Wang et al.

A model-based full-body dance generation and control framework combining MoCap, QP, TO, and MPC achieves dynamic stability and expressive motion in humanoid robots.

Shibowen Zhang, Jiayang Wu, Guannan Liu et al.

Proposes Sim2Real-AD, a modular framework combining GOB, PAM, TPT, for zero-shot transfer of VLM-guided RL policies to real vehicles, validated on Ford E-Transit.

Zilin Huang, Zhengyang Wan, Zihao Sheng et al.

SpatialVAM achieves data-efficient robot policy learning via 3D video diffusion, improving Meta-World success rates by 22%.

Peiyan Li, Yixiang Chen, Yuan Xu et al.

Advantage Reward Modeling (ARM) uses tri-state labels and a MIMO Transformer to estimate relative advantage, achieving 99.4% success in long-horizon towel-folding tasks.

Yiming Mao, Zixi Yu, Weixin Mao et al.

SMASH integrates onboard egocentric vision and scalable whole-body skill learning, enabling humanoid robots to perform continuous outdoor ping-pong without external sensors.

Junli Ren, Yinghui Li, Kai Zhang et al.

Proposes Bench2Drive-VL, integrating DriveCommenter for real-time closed-loop autonomous driving evaluation with multimodal reasoning.

Xiaosong Jia, Yuqian Shao, Zhenjie Yang et al.

DreamControl-v2 trains guided diffusion models directly in robot space, integrating diverse datasets to enhance scalability and automation for humanoid skills.

Sudarshan Harithas, Sangkyung Kwak, Pushkal Katara et al.

GenSplat enhances view generalization in robotic policy learning using 3D Gaussian Splatting.

Sen Wang, Huaiyi Dong, Jingyi Tian et al.

StreamingVLA achieves 2.4× speedup and 6.5× halting reduction via Action Flow Matching and Adaptive Early Observation.

Yiran Shi, Dongqi Guo, Tianchen Zhao et al.

VLA-OPD combines SFT and RL via Reverse-KL distillation, improving sample efficiency and robustness for Vision-Language-Action models.

Zhide Zhong, Haodong Yan, Junfeng Li et al.

DFM-VLA refines robot action sequences iteratively via discrete flow matching, achieving top performance on CALVIN benchmarks.

Jiayi Chen, Wenxuan Song, Jiaxin Fang et al.