Back to Arena

Second Me

by Mindverse (Shang, Li, et al.)

System Card

OrganizationMindverse (Shang, Li, et al.)
Released2025-03
Architecturehybrid / Personal LPM with SFT + DPO on user data
DetailsPersonalized "Large Personal Model" acts as an intelligent memory offload: retains, organizes, and dynamically uses user-specific knowledge. Trained via automated pipeline combining supervised fine-tuning with direct preference optimization on three personal tasks.
Parameters—
Domainpersonalizationagent-memorylifelong-learning
Open SourceYes
PaperView Paper
WebsiteVisit
CodeRepository
lpmsftdpopersonal-aiai-native-memory

Capability Profile

Benchmark Scores

6 of 14 benchmarks
Data Transparency:6 estimated
Long-Context Retrieval
0/5
RULER
no data
NIAH
no data
LooGLE
no data
LongBench
no data
∞Bench
no data
Multi-Turn Recall
2/2
LoCoMo
71.932pEstimated
MemoryBank
81.182pEstimated
Cross-Session Memory
1/1
LongMemEval
74.944pEstimated
Multi-Hop QA
1/3
BABILong
72.221pEstimated
MultiHop-RAG
no data
HotpotQA
no data
Agent Task Memory
1/1
AgentBench-Mem
7226pEstimated
Personalization
1/1
PerLTQA
84.673pEstimated
Factuality / Grounding
0/1
RAGAS
no data
Sources:Arena estimate — derived from capability profile, not independently verified