Top Papers in Computer Vision, NLP, Speech, Multimodal AI, Core ML, RecSys, and Graph ML
šš¼ Iāve put together a summary of key papers in #AI and categorized them into (i) need-to-know and (ii) good-to-know.
Fodev JEO
LATEST INVESTIGATIONS
Source audits & field notes
VectorEmbeddings are the backbone of AI/ML applications
Curiosity: Machines donāt understand human language & that is where we need embeddings.
Llama 3 implemented in pure NumPy
Curiosity: How can we understand LLM architectures at the most fundamental level?
RAG isn't dead, you just need a systematic workflow
Retrieval module, Augmentation module, and Generation module.
Top 6 ElasticSearch Use Cases
Curiosity: What makes Elasticsearch so versatile? How do organizations leverage its powerful search and analytics capabilities across different domainā¦
The giant leaps of open-source models for Vision Models
Curiosity: What insights can we retrieve from this? How does this connect to innovation in the field?
How to evaluate LLM Model?
Curiosity: What insights can we retrieve from this? How does this connect to innovation in the field?
![["Evalverse Space"]](/assets/img/news/Evalverse_2.jpeg)
All about the evaluation for LLMs.
Curiosity: How do we systematically evaluate LLM performance across diverse tasks?
![["Workflow"]](/assets/img/llm/Llamma-finetune.jpeg)
Llamma Finetune case ģ RLHF ģ ė¦¬
Curiosity: How can we fine-tune Llama 3 8B to beat GPT-3.5? What makes Salesforceās approach with Online Iterative RLHF so effective?
Hugging Face x Langchain
Curiosity: What happens when two major LLM ecosystems collaborate? How does this partnership benefit developers building LLM applications?
ģøźø° ķź·ø
Search article titles, categories, and tags. Full text is searched when needed.
Type to search articles.