6 papers
TartanMatch: Towards Universal Dense Correspondence Across Modalities
Hyeokjoon Kwon, Jiting Cai, Ruogu Li +7
Robotic platforms combine multi-modal sensors to operate across diverse conditions, but most dense correspondence methods are limited to RGB-RGB or a small set of modality pairs. T…
A new method for proving confluence on abstract reduction systems --- Confluence of non-E-overlapping weakly-shallow TRSs ---
Masahiko Sakai, Mizuhito Ogawa, Michio Oyamaguchi
This paper proposes a new method for proving the confluence of an abstract reduction system (ARS) by clarifying the sufficient conditions, called compatibility and edge commutativi…
IPR-1: Interactive Physical Reasoner
Mingyu Zhang, Lifeng Zhuo, Tianxi Tan +8
Humans learn by observing, interacting with environments, and internalizing physics and causality. Here, we aim to ask whether an agent can similarly acquire human-like reasoning f…
LuciBot: Automated Robot Policy Learning from Generated Videos
Xiaowen Qiu, Yian Wang, Jiting Cai +4
Automatically generating training supervision for embodied tasks is crucial, as manual designing is tedious and not scalable. While prior works use large language models (LLMs) or…
Architect: Generating Vivid and Interactive 3D Scenes with Hierarchical 2D Inpainting
Yian Wang, Xiaowen Qiu, Jiageng Liu +6
Creating large-scale interactive 3D environments is essential for the development of Robotics and Embodied AI research. Current methods, including manual design, procedural generat…
Take A Step Back: Rethinking the Two Stages in Visual Reasoning
Mingyu Zhang, Jiting Cai, Mingyu Liu +3
Visual reasoning, as a prominent research area, plays a crucial role in AI by facilitating concept formation and interaction with the world. However, current works are usually carr…