Algorithmic study of sub-fp16 KV cache compression on shared-memory mobile SoCs. Documented negative result: scalar sign+magnitude (incl. outlier extraction + 2-bit) insufficient vs KIVI. Cos sim shown unreliable for KV-quant PPL.

Negative result paper: the King Wen sequence has genuine anti-habituation statistical properties (confirmed via Monte Carlo against 100k baselines) but does not improve neural network training. Experiments on NVIDIA RTX 2060 (PyTorch) and Apple Silicon (MLX).

MoGRU: Momentum-Gated Recurrent Unit — When Second-Order Dynamics Help and When They Don't (negative-result research)

Content-aware adaptive sampling for Stable Diffusion - dynamically optimizing inference steps based on prompt complexity for 30-50% speedup with <5% quality loss.

Connectivity Contrast Index (CCI) and 17 alternative metrics across five EEG datasets — an honest non-replication report

A Windows 11 Bluetooth LE Audio/LC3 driver project targeting Qualcomm on x86-64 — with an explanation of why it can't work without an OEM or reverse-engineered driver for the hardware layer. Plus a tool to check LE Audio support on your PC. Not an installable driver.

Attempted dense-to-MoE conversion of Qwen 3.5 9B (DeltaNet hybrid) using CMoE and D2DMoE. Documents why post-hoc MoEfication fails on SwiGLU models without extensive sparsification. Negative result.