2026
an archive of posts from this year
| Oct 05, 2026 | Can Repeating Transformer Layers Help? |
|---|---|
| Sep 20, 2026 | Recurrent State and Depth: Two ‘new’ LLM Architectures |
| Aug 15, 2026 | TIRx GEMM - Detailed Technical Notes |
| Aug 15, 2026 | Python Syntax, PTX-Level Control - A GEMM at 98% of cuBLAS on Blackwell |
| Jun 19, 2026 | CUDA foundation |
| Jun 11, 2026 | From LunarLander to String-Stable Platooning |
| Jun 08, 2026 | RL fundamental-part 1 |
| May 29, 2026 | When Reward Chasing Meets Robustness |
| May 20, 2026 | Heuristic Learning for Control: Building a Harness Beyond Gradients |
| Apr 19, 2026 | KV Cache Management: Quantization and Compression |
| Mar 22, 2026 | Kimi Attention Residual: Rethinking Layer Connections in Transformers |
| Mar 09, 2026 | Action, Planning, and Memory: The Foundation of LLM Agents |
| Jan 20, 2026 | Mamba: Linear-Time Sequence Modeling with Selective State Spaces |
| Jan 08, 2026 | mHC: Manifold-Constrained Hyper-Connections |
| Jan 01, 2026 | ReAct: Synergizing Reasoning and Acting in Language Models |