KV-cache compression
InfiniPot-V
InfiniPot-V: Memory-Constrained KV Cache Compression for Streaming Video Understanding
Superseded baseline#47 of 234 most-superseded · first seen Jun 18, 2025
Superseded — cited as a baseline and beaten by newer methods
0 papers critique it · 3 beat it on benchmarks
Beaten on benchmarks
Head-to-head results where a newer method reports beating InfiniPot-V. Values are copied from the source paper's tables — verify against the cited paper.
DSCache beats InfiniPot-V
82.32 vs 76.40
StreamingBench (Real-time) · [Qwen2.5-VL-7B]
Decouple and Cache: KV Cache Construction for Streaming Video UnderstandingMuKV (DCP) beats InfiniPot-V
59.5 vs 57.9
Acc@Ego · [LLaVA-OV-7B, InfiniPot-V vs MuKV]
MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-AnsweringStreamMem beats InfiniPot-V
62.4 vs 60.8
VideoMME Medium · [Qwen2-VL-7B]
StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding
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Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.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 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