Huge congrats on the launch of ERNIE-Image — a major leap forward! We’re excited to see ERNIE-Image pushing the boundary of open text-to-image models with strong performance, efficient design, and real usability. Welcome everyone to try it out
@baiduresearch
-
PaddleOCR Surpasses Tesseract as Most-Starred OCR Project
By
–
PaddleOCR has surpassed 73.3K stars on GitHub—overtaking Google’s Tesseract (73.2K) to become the most-starred OCR project globally. GitHub: https://
github.com/PaddlePaddle/P
addleOCR
… PP-OCRv5: https://
arxiv.org/pdf/2603.24373 PaddleOCR-VL: https://
arxiv.org/pdf/2603.24326 -
PP-OCRv5: Compact Powerful Optical Character Recognition Model
By
–
Check out PP-OCRv5, our small yet powerful model specializing in OCR.
-
ERNIE 4.5 and ERNIE X1 Models Launch Announced
By
–
ERNIE 4.5 & ERNIE X1 are here! https://t.co/3EWmhfiM9d
— Baidu Research (@BaiduResearch) 16 mars 2025ERNIE 4.5 & ERNIE X1 are here!
-
Baidu World 2023 Live Stream Event Announcement
By
–
#BaiduWorld2023 will start in 3 hours! Watch the live stream 👇https://t.co/R9XFmAMIQX https://t.co/whb64ZALjm
— Baidu Research (@BaiduResearch) 16 octobre 2023#BaiduWorld2023 will start in 3 hours! Watch the live stream https://
x.com/i/broadcasts/1
yNGaZaeallJj
… -
HelixFold-Single: Fast MSA-Free Protein Structure Prediction
By
–
Sharing our latest paper on fast protein structure prediction in @NatMachIntell
! We introduce HelixFold-Single, an open-source, MSA-free method that competes well with MSA-based methods but is significantly faster. Read the paper below. -
Baidu World 2023: Foundation Models and Generative AI Ecosystem
By
–
Mark your calendars for #BaiduWorld2023 on Tuesday, Oct 17th at 10 am (UTC+8)! We'll be unveiling the latest in foundation models, AI-native apps, and the generative AI ecosystem. Catch the live event right here https://
x.com/i/broadcasts/1
yNGaZaeallJj
… -
Open-source Plans for AI Project Under Consideration
By
–
Thank Clement! We don't have an open-source plan for now, but we'll keep your interest in mind for future updates.
-
Adaptive Learning Boosts Interactive Reinforcement Feedback Efficiency
By
–
Tuesday 15:00, Paper TuBT17
Boosting Feedback Efficiency of Interactive Reinforcement Learning by Adaptive Learning from Scores
Paper: -
GOATS: Goal Sampling Adaptation for Robotic Scooping
By
–
Monday 9:40, Paper MoAT10
GOATS: Goal Sampling Adaptation for Scooping with Curriculum Reinforcement Learning
Project Website: https://
sites.google.com/view/goatscoop
ing
…