Unverified50% confidenceFactExact time
AdaMem is a relevance-guided soft compression framework that maps learned passage relevance estimates to query-dependent dynamic allocation of a fixed memory token budget.
1
Sources
50%
Confidence
Long-term
Relevance
9/22/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOrchSLM is a routing framework for analyzing small language model orchestration mechanisms, positioned as a unified analytical tool rather than a new orchestration approach65% similarUnverifiedAnthropic provides a thinking parameter control switch at the API level, as well as a budget_tokens parameter for setting the maximum number of tokens that the thinking process can consume.63% similarUnverifiedA micro LLM refers to a language model whose parameter count, memory footprint, and inference cost have all been significantly reduced.61% similarUnverified清晰的CLAUDE.md结构描述能让模型以更少的推理步骤找到正确信息，直接降低API调用成本61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/940071API
curl https://kongchang.com/api/v1/knowledge/claims/940071MCP
get_claim(id=940071)