activity
20192022
most citedDefensive Quantization: When Efficiency Meets Robustness

34 citations · 198 across the 21 of their papers we have counts for

collaborators

22 papers

cs.CL2022

Revisiting the Roles of "Text" in Text Games

Yi Gu, Shunyu Yao, Chuang Gan +2

Text games present opportunities for natural language understanding (NLU) methods to tackle reinforcement learning (RL) challenges. However, recent work has questioned the necessit…

cs.CV202216 cited

Weakly-Supervised Multi-Granularity Map Learning for Vision-and-Language Navigation

Peihao Chen, Dongyu Ji, Kunyang Lin +4

We address a practical yet challenging problem of training robot agents to navigate in an environment following a path described by some language instructions. The instructions oft…

cs.CV20228 cited

Learning Active Camera for Multi-Object Navigation

Peihao Chen, Dongyu Ji, Kunyang Lin +5

Getting robots to navigate to multiple objects autonomously is essential yet difficult in robot applications. One of the key challenges is how to explore environments efficiently w…

cs.LG202210 cited

Learning Physical Dynamics with Subequivariant Graph Neural Networks

Jiaqi Han, Wenbing Huang, Hengbo Ma +3

Graph Neural Networks (GNNs) have become a prevailing tool for learning physical dynamics. However, they still encounter several challenges: 1) Physical laws abide by symmetry, whi…

cs.CV202219 cited

Retrospectives on the Embodied AI Workshop

Matt Deitke, Dhruv Batra, Yonatan Bisk +36

We present a retrospective on the state of Embodied AI research. Our analysis focuses on 13 challenges presented at the Embodied AI Workshop at CVPR. These challenges are grouped i…

cs.CV20224 cited

RISP: Rendering-Invariant State Predictor with Differentiable Simulation and Rendering for Cross-Domain Parameter Estimation

Pingchuan Ma, Tao Du, Joshua B. Tenenbaum +2

This work considers identifying parameters characterizing a physical system's dynamic motion directly from a video whose rendering configurations are inaccessible. Existing solutio…