- Latest Transformer progress in LLM — Attention / MoE tricks, complexity and effective long context
- What Actually Makes Embedding Model Inference Fast
- The hidden Instability of LLM based AI
- Battle of Robustness: Gemini Flash 2.5 vs. GPT-5 on Noisy Sentiment Analysis
- AI Tricks and Techniques
- My Thoughts
- SOTA techniques in Deep Learning