Back to Arena

Titans

by lucidrains (community) / paper by Google Research

System Card

Organizationlucidrains (community) / paper by Google Research
Released2025-01
Architectureexternal-memory-network / Neural memory module (Memory-as-Context)
DetailsUnofficial reference PyTorch implementation of Google's Titans architecture: a learned NeuralMemory module that updates parameters at test time, combined with Memory-As-Context (MAC) transformer wrapping for long-term memory.
Parameters
Domainlong-contextlifelong-learning
Open SourceYes
neural-memorytest-time-learningtransformergoogle-research

Capability Profile

Benchmark Scores

8 of 14 benchmarks
Long-Context Retrieval
5/5
RULER
97.999p
NIAH
98.892p
LooGLE
81.395p
∞Bench
87.494p
Multi-Turn Recall
1/2
LoCoMo
68.622p
MemoryBank
no data
Cross-Session Memory
1/1
Multi-Hop QA
1/3
BABILong
82.496p
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