Unverified50% confidenceBenchmarkExact time
The two versions of MemT-1.0 on average outperform parametric memory baselines on memory-related tasks, remain competitive with retrieval-augmented methods, and largely preserve general capabilities.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/20/2026
First Seen
Valid until: 1/18/2027
Sources
Related Entities
Related Claims
UnverifiedMemT-1.0 designs a Mixture-of-Storage mechanism that partitions different levels of storage units inside the model, allocating and recalling them on demand to expand native memory capacity.69% similarUnverifiedMemGAS在LongMemEval-S上构建记忆处理约52.9M input tokens，Summary和Keyword带来的额外内存约27MB，约为原始记忆的10%65% similarUnverifiedOn the MemoryArena goal persistence evaluation, the Working Memory layer scores 55.31%, 8.4 percentage points higher than a pure summarization compression pipeline.64% similarUnverifiedThe benefit of a unified memory architecture is that data does not need to be copied back and forth between processors, giving lower latency and higher energy efficiency, which especially benefits graphics and machine learning tasks; but it also means memory capacity cannot be upgraded later, and the configuration at purchase is the configuration for life.64% similarUnverifiedHy-Memory 2.0 achieves 72.6% accuracy on the LoCoMo continuous memory evaluation.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1073326API
curl https://kongchang.com/api/v1/knowledge/claims/1073326MCP
get_claim(id=1073326)