Sitemap - 2024 - TechTalks
Where is Apple going with OpenELM?
Infinite contexts, fine-tuning, and RAG
What happens when LLM in-context learning scales to thousands of shots
LLM2Vec turns any LLM into a universal embedding model
Meta introduces another (potential) Transformer alternative
How LLMs and VLMs are revolutionizing robotics
ReFT outperforms PEFT methods in fine-tuning LLMs
How LLMs will kill Medium's business model
LLMs, from playing Street Fighter to real-time applications
Understanding the security of open-source machine learning models
Single-instruction fine-tuning of Llama-2
The fastest and most-efficient prompt compression technique
The alchemy of AI in material science
Creating foundational models through natural selection
RAFT fine-tunes LLMs for better RAG performance
Is cosine similarity the right measure for embedding models?
How to customize LLMs for topics they weren't trained for
How RelayAttention achieves high throughput on LLM applications
The implications of the Microsoft-Mistral AI partnership
Model-based reinforcement learnig with diffusion models
Wisdom beyond AI doom and acceleration
The implications of ChatGPT's unusual responses
Who will solve Sora's problems
How generative AI will change writing
How to avoid falling for deepfake scams
BizML: a framework for success in applied machine learning
What is Microsoft's "cheap generative AI" team doing?
How LLMs can self-improve on instruction-following
The winners and losers of the AI integration wars
ByteDance's new fine-tuning technique boost LLMs for reasoning tasks
Microsoft moves toward reducing dependence on OpenAI
Anthropic study sheds light on the vulnerabilities of LLM supply chains
How ChatGPT changed my writing process
Custom embedding models with small training dataset