RotateIt employs multimodal perception with vision and touch, trained in simulation, to enable multi-axis in-hand object rotation without fine-tuning in real-world.

Haozhi Qi, Brent Yi, Sudharshan Suresh et al.

Safety Chip adds LTL safety to LLM robots, reaching 100% safety in simulation.

Ziyi Yang, Shreyas S. Raman, Ankit Shah et al.

SafeShift uses counterfactual probing to identify safety-critical scenarios, reducing collision rates by 10% in autonomous driving trajectory prediction.

Benjamin Stoler, Ingrid Navarro, Meghdeep Jana et al.

Proposes CURB-SG, a multi-agent LiDAR-based urban 3D scene graph for enhanced environment understanding in autonomous driving.

Elias Greve, Martin Büchner, Niclas Vödisch et al.

Score-based grasping primitive GraspGF combined with residual RL achieves 56.5% success on diverse objects, outperforming baselines with high efficiency.

Tianhao Wu, Mingdong Wu, Jiyao Zhang et al.

SayNav uses large language models for dynamic navigation in new environments, improving success rate by 8%.

Abhinav Rajvanshi, Karan Sikka, Xiao Lin et al.

Lightweight EOAT combined with CMA-ES optimization achieves 100% success in robotic Lego assembly/disassembly.

Ruixuan Liu, Yifan Sun, Changliu Liu

Proposes Sequential Dexterity, using bi-directional RL to chain dexterous policies with transition feasibility, achieving 20% success boost in long-horizon tasks.

Yuanpei Chen, Chen Wang, Li Fei-Fei et al.

SWIM leverages human video data to train robot models, learning manipulation skills in under 30 minutes.

Russell Mendonca, Shikhar Bahl, Deepak Pathak

DriveAdapter employs feature alignment with adapters to decouple perception and planning, boosting autonomous driving performance.

Xiaosong Jia, Yulu Gao, Li Chen et al.

Proposes a goal-conditioned deep RL framework using tactile sensing for object pushing, trained in simulation with sim-to-real transfer, achieving over 90% success on unseen objects.

Max Yang, Yijiong Lin, Alex Church et al.

Hierarchical imitation learning enables robust multi-stage cable routing, improving success rate by 30% over end-to-end methods.

Jianlan Luo, Charles Xu, Xinyang Geng et al.

HIMOS uses hierarchical reinforcement learning for multi-object search in unknown environments, achieving over 90% success rate.

Fabian Schmalstieg, Daniel Honerkamp, Tim Welschehold et al.

Polybot aligns observation, action, and internal features across robots via wrist cameras, inverse kinematics, contrastive learning, and multi-head policies, enabling zero-shot transfer and improved success rates.

Jonathan Yang, Dorsa Sadigh, Chelsea Finn

Analyzed generalization gap in visual robotic manipulation using Factor World benchmark.

Annie Xie, Lisa Lee, Ted Xiao et al.

Proposes DE-TGN, a deep ensemble framework with Monte Carlo Dropout for human motion prediction and uncertainty quantification.

Kareem A. Eltouny, Wansong Liu, Sibo Tian et al.

RH20T dataset enables one-shot learning for diverse robotic skills with over 110,000 sequences.

Hao-Shu Fang, Hongjie Fang, Zhenyu Tang et al.

COMPASS employs differentiable causal discovery to identify key environment parameters, reducing sim-to-real trajectory differences by 40% and boosting task success to 85%.

Peide Huang, Xilun Zhang, Ziang Cao et al.

REFLECT combines hierarchical multimodal summaries with large language models for robot failure explanation and correction, achieving 88% explanation accuracy and 79% correction success.

Zeyi Liu, Arpit Bahety, Shuran Song

RVT employs a multi-view transformer with virtual view rendering, achieving 26% success improvement and 36x faster training on RLBench tasks.

Ankit Goyal, Jie Xu, Yijie Guo et al.