7 citations · 14 across the 11 of their papers we have counts for
7 papers · 1 filter
Evaluating Pretrained models for Deployable Lifelong Learning
Kiran Lekkala, Eshan Bhargava, Yunhao Ge +1
We create a novel benchmark for evaluating a Deployable Lifelong Learning system for Visual Reinforcement Learning (RL) that is pretrained on a curated dataset, and propose a novel…
3D Copy-Paste: Physically Plausible Object Insertion for Monocular 3D Detection
Yunhao Ge, Hong-Xing Yu, Cheng Zhao +5
A major challenge in monocular 3D object detection is the limited diversity and quantity of objects in real datasets. While augmenting real scenes with virtual objects holds promis…
DreamDistribution: Learning Prompt Distribution for Diverse In-distribution Generation
Brian Nlong Zhao, Yuhang Xiao, Jiashu Xu +6
The popularization of Text-to-Image (T2I) diffusion models enables the generation of high-quality images from text descriptions. However, generating diverse customized images with…
Value Explicit Pretraining for Learning Transferable Representations
Kiran Lekkala, Henghui Bao, Sumedh A. Sontakke +2
Understanding visual inputs for a given task amidst varied changes is a key challenge posed by visual reinforcement learning agents. We propose \textit{Value Explicit Pretraining}…
RoboCLIP: One Demonstration is Enough to Learn Robot Policies
Sumedh A Sontakke, Jesse Zhang, Sébastien M. R. Arnold +5
Reward specification is a notoriously difficult problem in reinforcement learning, requiring extensive expert supervision to design robust reward functions. Imitation learning (IL)…
Bird's Eye View Based Pretrained World model for Visual Navigation
Kiran Lekkala, Chen Liu, Laurent Itti
Sim2Real transfer has gained popularity because it helps transfer from inexpensive simulators to real world. This paper presents a novel system that fuses components in a tradition…
Beyond Generation: Harnessing Text to Image Models for Object Detection and Segmentation
Yunhao Ge, Jiashu Xu, Brian Nlong Zhao +3
We propose a new paradigm to automatically generate training data with accurate labels at scale using the text-to-image synthesis frameworks (e.g., DALL-E, Stable Diffusion, etc.).…