Method Drift›Long-context / context-window extension
Superseded baseline#40 of 53 most-superseded
D2O
D2O: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language ModelsLong-context / context-window extension · first seen Jun 18, 2024
superseded — cited as a baseline and beaten by newer methods
0 papers critique it · 1 beat it on benchmarks
Beaten on benchmarks
Head-to-head results where a newer method reports beating D2O. Values are copied from the source paper's tables — verify against the cited paper.
- FreqKV: Frequency Domain Key-Value Compression for Efficient Context Window Extension
FreqKV beats D2O · Avg. [LLaMA-2-chat-7B, 50% retaining ratio]
37.85 vs 36.37
- FreqKV: Frequency Domain Key-Value Compression for Efficient Context Window Extension
FreqKV beats D2O · Avg. [LLaMA-2-chat-7B, 1% retaining ratio]
35.54 vs 26.66
- FreqKV: Frequency Domain Key-Value Compression for Efficient Context Window Extension
FreqKV beats D2O · Avg. [LLaMA-3, 8K evaluation length]
87.68 vs 74.51
Newer alternatives
Recent methods in the same sub-problem, not yet superseded in the knowledge base.
- May 14, 2026