Authors: || Published: 2024-10-15T22:34:00 || Updated: 2024-10-15T22:34:00
Categories: || Tags: || Post-format: link
Recent AI Reading [15 October 2024]
Papers
Synthetic Data
AI Alignment with Human Feedback / Preferences
- The Perfect Blend: Redefining RLHF with Mixture of Judges
- RevisEval: Improving LLM-as-a-Judge via Response-Adapted References
- Better Instruction-Following Through Minimum Bayes Risk
- Tutor CoPilot: A Human-AI Approach for Scaling Real-Time Expertise
Retrieval-Augmented Generation
- A Comprehensive Survey on Vector Database: Storage and Retrieval Technique, Challenge
- Toward General Instruction-Following Alignment for Retrieval-Augmented Generation
Agentic AI
Other
- Let’s Verify Step by Step
- Blog post: Improving mathematical reasoning with process supervision
- Dataset: GitHub
- Training Language Models to Self-Correct via Reinforcement Learning
- Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- CoEdIT: Text Editing by Task-Specific Instruction Tuning
- Hyper-multi-step: The Truth Behind Difficult Long-context Tasks
- Were RNNs All We Needed?
- Intelligence at the Edge of Chaos
- RATIONALYST: Pre-training Process-Supervision for Improving Reasoning
- Towards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge with Curriculum Preference Learning
- From Generalist to Specialist: Adapting Vision Language Models via Task-Specific Visual Instruction Tuning
- MEGA-Bench: Scaling Multimodal Evaluation to over 500 Real-World Tasks
Technical Reports
Articles and Blog Posts
- Distance Metrics in Vector Search
- Introduction to Recurrent Neural Network
- Back Propagation in Recurrent Neural Networks
- Embeddings in Machine Learning: Everything You Need to Know
- Transformer Architecture: The Positional Encoding
- A Gentle Introduction to Positional Encoding in Transformer Models, Part 1
- What is the intuition behind the dot product attention?
- Transformers, Explained: Understand the Model Behind GPT-3, BERT, and T5
- The Illustrated Transformer
- Some Intuition on Attention and the Transformer
- How Transformers work in deep learning and NLP: an intuitive introduction
- AutoArena: An Open-Source AI Tool that Automates Head-to-Head Evaluations Using LLM Judges to Rank GenAI Systems