Ahead of AI
Ahead of AI focuses on machine learning and AI research and is read by more than 200,000 researchers and practitioners who want to stay ahead in a rapidly evolving field. Click to read Ahead of AI, by Sebastian Raschka, PhD, a Substack publication with hundreds of thousands of subscribers.
- Posts
- 33 from 4 Nov 2022 to 15 Jan 2025
- Posting
- monthly (18 in the last year)
- Kind
- personal blog
- Feed
- https://magazine.sebastianraschka.com/feed
2025 1
2024 1
2023 28
- Ten Noteworthy AI Research Papers of 2023
- Tackling Hallucinations, Boosting Reasoning Abilities, and New Insights into the Transformer Architecture
- Practical Tips for Finetuning LLMs Using LoRA (Low-Rank Adaptation)
- A Potential Successor to RLHF for Efficient LLM Alignment and the Resurgence of CNNs
- AI and Open Source in 2023
- LLM Business and Busyness: Recent Company Investments and AI Adoption, New Small Openly Available LLMs, and LoRA Research
- From Self-Alignment to LongLoRA
- LLM Training: RLHF and Its Alternatives
- The Missing Bits: Llama 2 Weights Have Changed
- New Foundation Models: CodeLlama and other highlights in Open-Source AI
- Llama 2, Flash-Attention 2, and More
- Large Language Models and Nearest Neighbors
- Long Contexts and Scaling Transformers to 1,000,000,000 Tokens
- State of Computer Vision 2023: From Vision Transformers to Neural Radiance Fields
- Accelerating PyTorch Model Training
- Understanding Encoder And Decoder LLMs
- Direct-Preference Optimization for Human Feedback and More
- LLM Tuning & Dataset Perspectives
- About LayerNorm Variants in the Original Transformer Paper, and Some Other Interesting Historical Tidbits About LLMs
- Finetuning LLMs Efficiently with Adapters
- Transformers for Long Inputs and Less Training Data
- Insights from Large-Scale LLM Training Runs
- Understanding Parameter-Efficient LLM Finetuning: Prompt Tuning And Prefix Tuning
- Finetuning Large Language Models
- Understanding Large Language Models
- Large Language Models 3.0
- TrAIn Differently: Do We Need Reinforcement Learning with Human Feedback (RLHF)?
- RevAIval of Ideas: From Next-Generation Convolutional Neural Networks to LLMs