Back to Arena

ICAE

by Microsoft Research (Ge et al.)

System Card

OrganizationMicrosoft Research (Ge et al.)
Released2023-07
Architecturekv-cache-extension / LoRA encoder + frozen decoder compressed memory slots
DetailsLoRA-adapted encoder compresses long contexts into a few memory-slot tokens that the frozen base LLM can condition on. Pretrained with autoencoding + LM objectives, then instruction-tuned.
Parameters—
Domainlong-context
Open SourceYes
PaperView Paper
CodeRepository
iclr-2024autoencoder4x-compressionlora

Capability Profile

Benchmark Scores

6 of 14 benchmarks
Data Transparency:6 estimated
Long-Context Retrieval
5/5
RULER
72.359pEstimated
NIAH
75.138pEstimated
LooGLE
78.768pEstimated
LongBench
603pEstimated
∞Bench
77.841pEstimated
Multi-Turn Recall
0/2
LoCoMo
no data
MemoryBank
no data
Cross-Session Memory
0/1
LongMemEval
no data
Multi-Hop QA
1/3
BABILong
70.810pEstimated
MultiHop-RAG
no data
HotpotQA
no data
Agent Task Memory
0/1
AgentBench-Mem
no data
Personalization
0/1
PerLTQA
no data
Factuality / Grounding
0/1
RAGAS
no data
Sources:Arena estimate — derived from capability profile, not independently verified