SafeHarness enhances robot manipulation safety with obstacle-aware planning, achieving 71.9% task success and 87.5% collision avoidance.

Bingxin Xu, Yuzhang Shang, Zhen Dong et al.

Introduced Workspace Models for lightweight robotic memory via saliency-driven supervision, achieving a 91.5% task success rate.

Nitish Dashora, Douglas Chen, Idan Shenfeld et al.

StageGuard learns stage transitions for long-horizon robot tasks via agentic distillation, significantly improving prediction accuracy.

Jinbang Huang, Yuanzhao Hu, Zhiyuan Li et al.

GeoAAC improves real-world task success rate from 53.3% to 74.4% through geometry-based adaptive action chunking.

Xin Chen, Sen Chen, Yujuan Ding et al.

Agile-WAM boosts robot control success by 29.4% with 11.9ms inference latency via multi-horizon multimodal prediction.

Hanchu Zhou, Brendan Lynch, Raman Goyal et al.

OPTED fine-tunes end-to-end driving policies using a render-free teacher, improving driving scores by 1.6x and 9.5x.

Damiano Da Col, Maximilian Igl, Peter Karkus et al.

MILER achieves zero-shot sim-to-real transfer in unstructured environments using semantic mid-level representation.

Thomas Steinecker, Denis Trescher, Alexander Bienemann et al.

Proposes an underwater visual target tracking method combining target-specific depth estimation and adaptive model-fusion predictive control, outperforming existing frameworks.

Yuheng Zhou, Haiyang Cheng, Yanqi Feng et al.

MoWAM improves robot policy learning efficiency via explicit future motion prediction, showing strong performance on LIBERO dataset.

Jiayu Wang, Bin Zhu, Yue Yu et al.

Improving marine perception with OceanSim's synthetic data generation pipeline.

Haoyu Ma, Onur Bagoren, Anja Sheppard et al.

ActiveScale enhances robot active perception through model, data, and hardware design, significantly improving task success rates.

Shuai Zhou, Kaisheng Pang, Wenxuan Song et al.

DIDO effectively predicts future dynamics in robotic manipulation with one-step denoising, achieving a 99.0% success rate.

Jing Lyu, Shuanghao Bai, Runze Xiao et al.

UniMPA addresses transition realizability in VLA models via action-grounded transition modeling.

Wei Li, Rui Shao, Jie He et al.

FARM reads frozen VLA-JEPA states with 33,985 parameters, reaching 85.68% AUROC and 88.59% AUPRC.

Haoran Pei, Mingrui Luo, Senbao Wang et al.

Using bound propagation to verify steering in unseen conditions for autonomous vehicles.

Menuka Ghalan, Charles Rodgers, Zachary D. Asher

DUET-DINO enables 7-DoF robot planning via cross-view latent world modeling, achieving 92%-60% task success rates.

Nisarga Nilavadi, Ralf Römer, Moritz Reuss et al.

FreqFM improves VLA models by frequency conditioning, achieving a 9.3-point gain on LIBERO-Plus.

Haochen Niu, Shengye Dong, Hao Liu et al.

DRiF framework uses data-driven risk fields for safer end-to-end driving, achieving 88.78 driving score on Bench2Drive.

Yuanxin Tian, Zhiyuan Liu, Jinhao Li et al.

Proposed CAMF achieves 91.86% intention recognition accuracy for industrial human-robot collaboration.

Xinyu Liu, Qiqi Dong, Boya Jia et al.

ContextFlow uses conditional flow matching for fine-tuning-free robot adaptation, reaching 73.5% average LIBERO success and surpassing ICRT by 35 points.

Jian Ding, Xianjie Dai, Roei Herzig et al.