Aniruddha Kembhavi, Roozbeh Mottaghi, Luca Weihs, Kiana Ehsani, Alvaro Herrasti, Winson Han, Eric Kolve, Eli Vanderbilt
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Figure 1: We address the problem of visual object manipulation, where the goal is to move an object between two locations in a scene. Operating in visually rich and complex environments, generalizing to unseen environments and objects, avoiding collisions with objects and structures in the scene, and visual planning to reach the destination are among the major challenges of this task. Here, we illustrate a sequence of actions taken a by a virtual robot within the AI2-THOR environment for picking up a vase from the shelf and stack it on a plate on the countertop.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2104.11213")
get_code_for_paper("2104.11213")
have("2104.11213")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2104.11213.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2104.11213)
Connect an agent — have() is free.