6/ Nougat – proposes an approach for neural optical understanding of academic documents; it supports the ability to extract text, equations, and tables from academic PDFs, i.e., convert PDFs into LaTeX/markdown.
RESEARCH
-
FacTool: Detecting Factual Errors in LLM Generated Text
By
–
7/ Factuality Detection in LLMs – proposes a tool called FacTool to detect factual errors in texts generated by LLMs; shows the necessary components needed and the types of tools to integrate with LLMs for better detecting factual errors.
-
AnomalyGPT: Industrial Anomaly Detection Vision-Language Model
By
–
8/ AnomalyGPT – an approach for industrial anomaly detection based on large vision-language models; it simulates anomalous images and textual descriptions to generate training data; employs an image decoder and prompt learner to detect anomalies.
-
Graph of Thoughts: Network Reasoning Approach for LLMs
By
–
4/ Graph of Thoughts – a prompting approach that models text generated by LLMs as an arbitrary graph; enables combining arbitrary "thoughts" and enhancing them using feedback loops; the core idea is to enhance the LLMs through "network reasoning".
-
MVDream: Multi-View Diffusion Model for 3D Image Generation
By
–
5/ MVDream – a multi-view diffusion model that can generate geometrically consistent multi-view images given a text prompt; it leverages pre-trained diffusion models and a multi-view dataset rendered from 3D assets.https://t.co/wlsC7DRViB
— DAIR.AI (@dair_ai) 3 septembre 20235/ MVDream – a multi-view diffusion model that can generate geometrically consistent multi-view images given a text prompt; it leverages pre-trained diffusion models and a multi-view dataset rendered from 3D assets.
-
Large Language and Speech Model Enables Natural Conversational AI
By
–
1/ Large Language and Speech Model – proposes a large language and speech model trained with cross-modal conversational abilities that supports speech-and-language instruction enabling more natural interactions with AI systems.
-
Top ML Research Papers: AnomalyGPT, SAM-Med2D, Graph of Thoughts
By
–
Top ML Papers of the Week (Aug 28 – Sep 3): – AnomalyGPT
– SAM-Med2D
– Graph of Thoughts
– Factuality Detection in LLMs
– Large Language and Speech Model
– Vector Search with OpenAI Embeddings
… -
Why Adults Stop Deep Technical Work After School
By
–
i was doing math problems on the plane (usamo 2023!) and the flight attendant asked me if I was doing schoolwork (flattering age-wise she thought I was in school) it’s a total shame that most people stop doing any technical or quantitative deep work post-school, esp on pen&paper
-
Building Semantic Search Apps with ChromaDB Vector Database
By
–
Great article by @avikumart_ on building a Semantic Search app using the #opensource vector database ChromaDB (
@trychroma
)! https://
medium.com/ai-science/bui
ld-semantic-search-applications-using-open-source-vector-database-chromadb-a15e9e7f14ce
… #LLMs -
Google Sponsors Deep Learning Indaba 2023 Conference
By
–
We’re proud to be a Sponsor of the annual @DeepIndaba meeting, held this week at the University of Ghana in Accra, Ghana. Registered for #Indaba2023? We hope you’ll visit the Google booth to learn more about our ML research! Learn more about Indaba → https://
deeplearningindaba.com/2023/