One critical challenge with continual learning or adding new domain knowledge is catastrophic forgetting, the decline of base model performance with new domain data. Our training methodology overcomes this and not only we progressively improve cultural understanding with more
RESEARCH
-

CulturalGround Fine-tuning Achieves State-of-the-Art Performance on Cultural Benchmarks
By
–
To demonstrate the effectiveness of CulturalGround, we fine-tune an existing multimodel model Pangea on a subset of the dataset. The resulting model achieves state-of-the-art performance for its model size on multiple cultural benchmarks in PangeaBench and other benchmarks. Below
-

CulturalPangea Excels in Multilingual and English Performance
By
–
CulturalPangea not only achieves good performance on multilingual cultural understanding, but also perform well on English, and overall.
-

CulturalGround: Building Inclusive Multimodal LLMs for Global Contexts
By
–
Current multimodal LLMs excel in English and Western contexts but struggle with cultural knowledge from underrepresented regions and languages. How can we build truly globally inclusive vision-language models? We are introducing CulturalGround, a large-scale dataset with 22M
-

CulturalGround: Scalable Multilingual VQA Data Pipeline from Wikidata
By
–
CulturalGround data construction: We designed a scalable pipeline to create culturally grounded multilingual VQA data from Wikidata, a structured knowledge base. Our data curation pipeline:
– Cultural Entity Selection: Extract 3M+ culturally relevant entities from Wikidata -

Meta’s Focus on Geometric Computer Vision for Spatial Video Capture
By
–
There have been a lot of crazy many-camera rigs created for the purpose of capturing full spatial video. I recall a conversation at Meta that was basically “we are going to lean in as hard as possible on classic geometric computer vision before looking at machine learning
-
Embodied Intelligence and AI Systems Interacting with Physical World
By
–
Ask us your questions about embodied intelligence or AI systems that interact w/the world. We’re featuring a few in an upcoming explainer w/MIT prof. Vincent Sitzmann (
@vincesitzmann
). For more on his work: https://
vincentsitzmann.com -

LLM Performance Drops on Non-Standard Medical Questions
By
–
Another example of a persistent problem with LLMs. They do very well on standard medical questions, but when the right answer is replaced with “none of the above” performance drops. More recent models generally have lower drops in performance. https://
jamanetwork.com/journals/jaman
etworkopen/fullarticle/2837372
… -

Top Artificial Intelligence Books for Career Growth and Learning
By
–
Explore TOP #Artificialintelligence Books for reading, learning, growing your knowledge and advancing your career: http://
amzn.to/2YRE6Sj
——— ———
#DataScience #DataMining #MachineLearning #AI #DeepLearning #Mathematics #GenerativeAI #LLMs #Algorithms #DataScientist #Python -

Learn Quantum Computing with Python and IBM Quantum Platform
By
–
Learn #QuantumComputing with #Python and IBM Quantum — Write your own practical quantum programs with Python [2nd Edition]: http://
amzn.to/3F3PdlD via @PacktDataML ——
𝓦𝓱𝓪𝓽 𝓨𝓸𝓾 𝓦𝓲𝓵𝓵 𝓛𝓮𝓪𝓻𝓷: Get familiar with the features within the IBM Quantum Platform
