Waiting to Decompress: The Economics of LLM-Based Compression
Summary: Benchmarked and speed‑optimized LLM-based compression methods and introduced a cost model quantifying runtime–cost tradeoffs. Finds current economics: ~10 years to amortize compute vs storage and ~120 years to beat traditional compressors, though hardware/model efficiency trends could make LLM compression viable within a decade. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Andreas Kipf
- 2. Tobias Schmidt
- 3. Ping-Lin Kuo
- 4. Skander Krid
- 5. Moritz Rengert
- 6. Luca Heller
- 7. Andreas Zimmerer
- 8. Mihail Stoian
- 9. Varun Pandey
- 10. Alexander van Renen
Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 0 of 0 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next