Method Drift›KV-cache compression
Superseded baseline#73 of 234 most-superseded
InfiniPot
KV-cache compression
superseded — cited as a baseline and beaten by newer methods
1 papers critique it · 1 beat it on benchmarks
What papers say
Verbatim critique sentences, each from a paper that cites InfiniPot as a baseline.
“it limits in selecting salient frame regions in spatial domain, failing to analyze across temporal frames and segments”
— MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering
Beaten on benchmarks
Head-to-head results where a newer method reports beating InfiniPot. Values are copied from the source paper's tables — verify against the cited paper.
- EpiCache: Episodic KV Cache Management for Long Conversational Question Answering
EpiCache beats InfiniPot · Avg [LLaMA3.2-3B / LoCoMo]
27.6 vs 13.3
- EpiCache: Episodic KV Cache Management for Long Conversational Question Answering
EpiCache beats InfiniPot · Avg [LLaMA3.2-3B / Realtalk]
30.5 vs 16.8
- EpiCache: Episodic KV Cache Management for Long Conversational Question Answering
EpiCache beats InfiniPot · Avg [LLaMA3.1-8B / LoCoMo]
36.3 vs 16.7
- EpiCache: Episodic KV Cache Management for Long Conversational Question Answering
EpiCache beats InfiniPot · Avg [LLaMA3.1-8B / Realtalk]
37.8 vs 20.5
Newer alternatives
Recent methods in the same sub-problem, not yet superseded in the knowledge base.
- May 21, 2026
- KVCapsuleKVCapsule: Efficient Sequential KV Cache Compression for Vision-Language Models with Asymmetric RedundancyMay 14, 2026
- Decoupled Streaming Cache (DSCache)Decouple and Cache: KV Cache Construction for Streaming Video UnderstandingMay 3, 2026
- May 1, 2026
- Hierarchical Adaptive Eviction (HAE)Hierarchical Adaptive Eviction for KV Cache Management in Multimodal Language ModelsFeb 2, 2026
- Dec 13, 2025
- StreamKVStreamKV: Streaming Video Question-Answering with Segment-based KV Cache Retrieval and CompressionNov 10, 2025