Monday 9:40, Paper MoAT10
GOATS: Goal Sampling Adaptation for Scooping with Curriculum Reinforcement Learning
Project Website: https://
sites.google.com/view/goatscoop
ing
…
@baiduresearch
-
GOATS: Goal Sampling Adaptation for Robotic Scooping
By
–
-
Robotics Lab Showcases Autonomous Driving and Control Research at IROS2023
By
–
Our Robotics and Autonomous Driving Lab is geared up for #IROS2023 this week in Detroit! We will present research on robotic control, NeRF for driving view simulation, and adaptive learning. Swing by Booth 532 to explore more or connect if you're around! 🧵 pic.twitter.com/r83ZHfNIS4
— Baidu Research (@BaiduResearch) 2 octobre 2023Our Robotics and Autonomous Driving Lab is geared up for #IROS2023 this week in Detroit! We will present research on robotic control, NeRF for driving view simulation, and adaptive learning. Swing by Booth 532 to explore more or connect if you're around!
-
VideoGen: Reference-Guided Latent Diffusion for Video Generation
By
–
We proposed a new text-to-video generation approach, VideoGen, which can generate high-definition video with high frame fidelity and strong temporal consistency using reference-guided latent diffusion. Learn more: https://t.co/HS5ALQv3GK pic.twitter.com/aEoUls78eS
— Baidu Research (@BaiduResearch) 7 septembre 2023We proposed a new text-to-video generation approach, VideoGen, which can generate high-definition video with high frame fidelity and strong temporal consistency using reference-guided latent diffusion. Learn more: https://
videogen.github.io/VideoGen/ -
Baidu Hosts Foundation Models Workshop at CVPR2023
By
–
Baidu was proud to co-host the inaugural "Workshop on Foundation Models" at #CVPR2023 last week with ZJU, HKU, and AIR-CAS. https://
foundation-model.com/home Congrats to CTRL & njust for their wins in Multi-Task & Cross-Modal tracks! Check out Baidu's CV models: https://
github.com/PaddlePaddle/V
IMER
… -
StyleSync: AI Project for Creative Content Generation
By
–
You can find more details on the project page. https://
hangz-nju-cuhk.github.io/projects/Style
Sync
… -
StyleSync: High-Fidelity Generalized Personalized Lip Sync
By
–
Demo video for the paper: StyleSync: High-Fidelity Generalized and Personalized Lip Sync in Style-based Generator (CVPR 2023).
-
StyleSync: High-Fidelity Lip Synchronization Framework
By
–
We propose StyleSync, an effective framework that enables high-fidelity lip synchronization. We identify that a style-based generator would sufficiently enable such a charming property on both one-shot and few-shot scenarios. Read more: https://t.co/IVP6DmaFFF #CVPR2023 pic.twitter.com/6r7on4uqUp
— Baidu Research (@BaiduResearch) 22 juin 2023We propose StyleSync, an effective framework that enables high-fidelity lip synchronization. We identify that a style-based generator would sufficiently enable such a charming property on both one-shot and few-shot scenarios. Read more: https://
arxiv.org/abs/2305.05445 #CVPR2023 -
Semi-DETR: Transformer-Based Semi-Supervised Object Detection
By
–
We proposed Semi-DETR, the first Transformer-based end-to-end semi-supervised object detector. Results outperform all SOTA methods on COCO & Pascal VOC by clear margins. Read more: https://
openaccess.thecvf.com/content/CVPR20
23/papers/Zhang_Semi-DETR_Semi-Supervised_Object_Detection_With_Detection_Transformers_CVPR_2023_paper.pdf
… #CVPR2023 -
CAPE: Novel 3D Object Detection Using Local Camera Coordinates
By
–
We propose a novel method, CAPE, for 3D object detection by using local camera-view coordinates, not global. This extends to temporal modeling, boosting detection, and leads to SOTA LiDAR-free performance. #CVPR2023 Paper: https://
arxiv.org/abs/2303.10209 Code: https://
github.com/PaddlePaddle/P
addle3D
… -
Comate Built on ERNIE-Code: Unified Model for 116 Languages
By
–
Comate is built on ERNIE-Code, a unified pre-trained language model for 116 NLs and 6 PLs. Read more: https://t.co/K0aII1wwQg #LLM https://t.co/tSRHiHdZQr
— Baidu Research (@BaiduResearch) 7 juin 2023Comate is built on ERNIE-Code, a unified pre-trained language model for 116 NLs and 6 PLs. Read more: https://
arxiv.org/abs/2212.06742 #LLM