Unverified50% confidenceFactExact time
REMORY's encoder accepts raw history of up to 64K tokens and a human-readable summary of approximately 250 tokens, using a 12-layer Transformer with a 768-dimensional hidden state.
1
Sources
50%
Confidence
Long-term
Relevance
10/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedREMORY's residual decoder generates a bounded soft token sequence, each a 768-dimensional vector, stopping after N ≤ 64 tokens.77% 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%70% similarVerifiedTaking the LLaMA-2 70B model as an example, a sequence of 2048 tokens requires approximately 4 GB of VRAM for the KV cache alone.70% similarUnverifiedOn a 64-bit system, a struct containing a 1-byte char and an 8-byte long may occupy 16 bytes rather than 9 bytes due to memory alignment, resulting in a waste rate as high as 44%.69% similarUnverifiedREMORY claims that a residual vector sequence of 32 dimensions can recover an 8K-token conversation with 95% fidelity.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/998480API
curl https://kongchang.com/api/v1/knowledge/claims/998480MCP
get_claim(id=998480)