Authors: || Published: 2025-08-11T20:59:00 || Updated: 2025-08-13T22:41:00 || 1 min read
Categories: || Tags: || Post-format: link
Recent AI Reading [11 August 2025]
Papers
Agentic AI
AI Alignment with Human Feedback and Preferences, and other methods
Large Language Models
- Learning without training: The implicit dynamics of in-context learning
- Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning
Retrieval-Augmented Generation
Embodied AI
Miscellaneous
- Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation
- Writing is thinking
- AlphaGo Moment for Model Architecture Discovery
- Working with AI: Measuring the Occupational Implications of Generative AI
Technical Reports
- Kimi K2: Open Agentic Intelligence
- Apple Intelligence Foundation Language Models Tech Report 2025
- AI-enabled scientific revolution in the age of generative AI: second NSF workshop report
Articles and Blog Posts
- Prompt engineering overview
- How to Build an Agent
- Understanding LLMs from Scratch Using Middle School Math
- Understanding reinforcement learning for model training from scratch
- Agent Learning from Human Feedback (ALHF): A Databricks Knowledge Assistant Case Study