7/ Red Teaming Visual Language Models – finds that 10 prominent open-sourced VLMs struggle with red teaming and have up to 31% performance gap with GPT-4V; applies red teaming alignment to LLaVA-v1.5 with SFT to improve performance by 10%.
GENERATIVE AI
-
Diffuse to Choose: Diffusion-Based Image Inpainting Model
By
–
4/ Diffuse to Choose – a diffusion-based image-conditioned inpainting model to balance fast inference with high fidelity while enabling accurate semantic manipulations in a given scene content.https://t.co/KUJjxVfCHc
— DAIR.AI (@dair_ai) 28 janvier 20244/ Diffuse to Choose – a diffusion-based image-conditioned inpainting model to balance fast inference with high fidelity while enabling accurate semantic manipulations in a given scene content.
-
WARM: Weighted Averaged Rewards Models Improve LLM Alignment
By
–
5/ WARM – introduces weighted averaged rewards models (WARM) that involve fine-tuning multiple rewards models and then averaging them in the weight space; improves efficiency while improving the quality and alignment of LLM predictions.
-
Top Machine Learning Papers Week January 22-28
By
–
The Top ML Papers of the Week (Jan 22 – Jan 28): – WARM
– Medusa
– AgentBoard
– MambaByte
– Knowledge Fusion of LLMs
– Resource-efficient LLMs & Multimodal Models
… -
AI advances in medical diagnostic error eradication efforts
By
–
Towards the eradication of medical diagnostic errors.
Can advances in #AI help get us there?
A new Ground Truths post, link in profile -
LangChain Improves Function and Tool Calling Documentation
By
–
Updated tool calling docs More and more model APIs are starting to expose `function` and `tool` calling parameters We've improved the DevEx around this, and updated key docs Function calling guide: https://
python.langchain.com/docs/modules/m
odel_io/chat/function_calling
… Tool calling output parser: https://
python.langchain.com/docs/modules/m
odel_io/output_parsers/types/openai_tools
… -
Mathematics and Art Intersection in Data Science and AI
By
–
Math and Art! #BigData #Analytics #DataScience #AI #MachineLearning #IoT #IIoT #PyTorch #Python #RStats #TensorFlow #Java #JavaScript #ReactJS #GoLang #CloudComputing #Serverless #DataScientist #Linux #Books #Programming #Coding #100DaysofCode https://
geni.us/Math-Art -
LLMs Face Text Data Scarcity, Video Data Offers New Opportunities
By
–
LLMs may be running out of text data: they've already scraped most of the web.
— Erik Brynjolfsson (@erikbryn) 28 janvier 2024
But beyond that, there are many other types of data, notably video. But that will require new approaches.@DaphneKoller and @ylecun explain it well in this short clip.https://t.co/spaJV6Io3YLLMs may be running out of text data: they've already scraped most of the web. But beyond that, there are many other types of data, notably video. But that will require new approaches. @DaphneKoller and @ylecun explain it well in this short clip.
-
Video datasets and emerging approaches as next frontier
By
–
Yep. And there are other approaches, using the much, much larger data sets of video (and other types of data) that could be the next frontier.
