I am glad I inspired your career in ML. I will resume sharing them again 🙂
@jeande_d
-
ML Fundamentals Chapter Ranks Top in Search Results
By
–
Super cool to see chapter 11 "ML Fundamentals" in Complete Machine Learning Package ranking on top of search results for a small query like "ml fundamentals", ahead of big players like Google & Microsoft! This is a reflection of how much people enjoy learning the content and
-
Correction: NaturalBench collaboration between CMU and University of Washington
By
–
Correction: NaturalBench was a fruitful collaboration between CMU and University of Washington.
-
Pangea: Open Multilingual Multimodal LLM for 39 Languages
By
–
Pangea: A Fully Open Multilingual Multimodal LLM for 39 Languages
—————————–
Paper: https://
arxiv.org/abs/2410.16153
Project website: https://
neulab.github.io/Pangea/
Model: https://
huggingface.co/neulab/Pangea-
7B
…
Extended post by @xiangyue96 : -
NaturalBench: Vision-Language Models Evaluation on Adversarial Samples
By
–
Here are links to the projects and related Twitter posts NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples
—————————–
Paper: https://
arxiv.org/abs/2410.14669
Project website: https://
linzhiqiu.github.io/papers/natural
bench/
…
Extended post by @ZhiqiuLin
: -
CMU releases NaturalBench for multimodal LLM evaluation
By
–
This week, we(two amazing research groups at CMU) released two projects in multimodal evaluation and multilingual multimodal LLMs. – NaturalBench: A vision-centric VQA evaluation benchmark that challenges all leading multimodal LLMs while using natural images and simple
-
Pangea: New Multilingual Multimodal LLM Supporting 39 Languages
By
–
Pangea is a new multilingual multimodal LLM that understands and responds in 39 languages. Pangea outperforms existing open source multimodal LLMs including recent models like Llama-3.2-Vision, Molmo, and LlavaOneVision. The release package is a deluxe buffet of model, 6M
-
NaturalBench: Vision-Centric VQA Benchmark for Compositional Reasoning
By
–
NaturalBench is a robust, vision-centric, bias-free VQA benchmark for evaluating compositional reasoning in visual language models(VLMs). A whole thread about NaturalBench and why it is an important benchmark in multimodal community
-
Deep Learning and Computational Physics Lecture Notes USC
By
–
Deep Learning and Computational Physics – Lecture Notes, University of South California Great and concise notes on various fundamental topics in deep learning, drawing connections between computational physics and deep learning. The notes got a nice structure. Starts from the
-
Deep Learning and Computational Physics Lecture Notes Introduction
By
–
Deep Learning and Computational Physics (Lecture Notes) https://
arxiv.org/abs/2301.00942
v1
… Full abstract: The main objective of these notes is to introduce a student who is familiar with concepts in linear algebra and partial differential equations to select topics in deep learning.