Long-context / context-window extension
D2O
D2O: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models
Superseded baseline#40 of 53 most-superseded · first seen Jun 18, 2024
Superseded — cited as a baseline and beaten by newer methods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 beats D2O
35.54 vs 26.66
Avg. · [LLaMA-2-chat-7B, 1% retaining ratio]
FreqKV: Frequency Domain Key-Value Compression for Efficient Context Window Extension
What to use instead
Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.
- May 14, 2026