6 papers
CounterAlign: Counterfactual Supervision for Vision-Language-Action Models
Haru Kondoh, Kei Ota, Asako Kanezaki +1
Vision-Language-Action (VLA) models are typically trained with behavior cloning (BC) on expert demonstrations. However, BC provides only positive supervision for expert actions, wi…
Touch2Insert: Zero-Shot Peg Insertion by Touching Intersections of Peg and Hole
Masaru Yajima, Yuma Shin, Rei Kawakami +2
Reliable insertion of industrial connectors remains a central challenge in robotics, requiring sub-millimeter precision under uncertainty and often without full visual access. Visi…
Modality Selection and Skill Segmentation via Cross-Modality Attention
Jiawei Jiang, Kei Ota, Devesh K. Jha +1
Incorporating additional sensory modalities such as tactile and audio into foundational robotic models poses significant challenges due to the curse of dimensionality. This work ad…
FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models
Kuanting Wu, Kei Ota, Asako Kanezaki
Video Diffusion Models (VDMs) can generate high-quality videos, but often struggle with producing temporally coherent motion. Optical flow supervision is a promising approach to ad…
Zero-Shot Peg Insertion: Identifying Mating Holes and Estimating SE(2) Poses with Vision-Language Models
Masaru Yajima, Kei Ota, Asako Kanezaki +1
Achieving zero-shot peg insertion, where inserting an arbitrary peg into an unseen hole without task-specific training, remains a fundamental challenge in robotics. This task deman…
Tactile Estimation of Extrinsic Contact Patch for Stable Placement
Kei Ota, Devesh K. Jha, Krishna Murthy Jatavallabhula +2
Precise perception of contact interactions is essential for fine-grained manipulation skills for robots. In this paper, we present the design of feedback skills for robots that mus…