Unverified50% confidenceBenchmarkExact time
Compared with the individual baselines under each setting, CoLFA reduced token consumption by up to 97.6%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/13/2026
First Seen
Valid until: 2/11/2027
Sources
Related Entities
Related Claims
UnverifiedMLA can further reduce KV Cache usage by approximately 93% compared to GQA.71% similarUnverifiedThe distilled artifact reduces downstream API overhead by an average of 19.7%.68% similarUnverified代码执行方案将相同任务的token消耗从15万降至2000,减少了98.7%67% similarUnverifiedCompared with the most efficient competitive multimodal baseline, HiVe-Mem reduces token consumption by about 90%.66% similarUnverifiedThe residual safety filter reduces drops by 75% while still completing 91.5% of the goals.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1165463API
curl https://kongchang.com/api/v1/knowledge/claims/1165463MCP
get_claim(id=1165463)