Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,694 papers · 148 categories

Trend · papers per month

count% of corpus
0111 · Oct 202319922001200920172026
1 result for “RASP”
What Algorithms can Transformers Learn? A Study in Length Generalizationcs.LG

Study shows Transformers can generalize to varying task lengths.

problem Understanding when and how Transformers can generalize to different input lengths.
method Proposed a unifying framework and introduced the RASP-Generalization Conjecture.
result Transformers tend to length generalize on tasks if solvable by short RASP programs.
Transformerslength generalizationRASPmin-degree-interpolatoralgorithmic tasks
2023-10-24abs ↗pdf ↗