ArXiv TLDR

Tetsuya Ogata

3 papers · Latest:

Robotics

How to utilize failure demo data?: Effective data selection for imitation learning using distribution differences in attention mechanism

This paper proposes a method to effectively use failure demonstration data in imitation learning by learning success-failure discrepancies in attention mechanisms.

2605.07560
Robotics

MSACT: Multistage Spatial Alignment for Stable Low-Latency Fine Manipulation

MSACT introduces a multistage spatial attention module for stable 2D attention point extraction and temporal alignment, improving low-latency fine manipulation.

2605.00475
Robotics

Stereo Multistage Spatial Attention for Real-Time Mobile Manipulation Under Visual Scale Variation and Disturbances

A new stereo spatial attention method enables robust mobile manipulation in dynamic environments, handling visual scale variations and disturbances.

2605.00471

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.