mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local - tobi/qmd

formalizing econometrics. Contribute to apoorvalal/lean-hansen-econometrics development by creating an account on GitHub.

The representation degeneration problem is a phenomenon that is widely observed among self-supervised learning methods based on Transformers. In NLP, it takes the form of anisotropy, a singular property of hidden representations which makes them unexpectedly close to each other in terms of angular distance (cosine-similarity). Some recent works tend to show that anisotropy is a consequence of optimizing the cross-entropy loss on long-tailed distributions of tokens. We show in this paper that anisotropy can also be observed empirically in language models with specific objectives that should not suffer directly from the same consequences. We also show that the anisotropy problem extends to Transformers trained on other modalities. Our observations suggest that anisotropy is actually inherent to Transformers-based models.

glues pretrained models to do stem separation and transcription to help learn music by ear. - apoorvalal/mlodies

How we use an eighty-year-old algorithm to find arbitrages in the cloud market.

Comments & analysis: Colonel Fazackerley Butterworth-Toast / Bought an old castle complete with a ghost,

YouTube video by 48bytes

This documents the workflow used to convert the LaTeX methods notes into Quartz chapter notes, plus a debrief of what was required in practice.

A structured set of methods notes migrated from the LaTeX source in 00_methods_notes.

gist This note documents a small end‑to‑end experiment: run a local Qwen3‑VL multimodal model via llama.cpp’s llama-server, use it as a VLM classifier on EuroSAT (satellite land‑use classes), and then...